论文下载百度云链接：链接：https://pan.baidu.com/s/100OAXTIOTPoMjbi-dwOcxA 
提取码：请关注【计算机视觉联盟】微信公众号，回复：NIPS2019

今天更新到2019年9月6号

目录

今天更新到2019年9月4号

Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology

多模态元学习，Toward Multimodal Model-Agnostic Meta-Learning

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation

RUBi: Reducing Unimodal Biases in Visual Question Answering 

理解图神经网络中的注意力与泛化机制，Understanding Attention and Generalization in Graph Neural Networks

Facebook提出跨语言预训练模型XLM，Cross-lingual Language Model Pretraining

超图卷积神经网络， HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs

四元知识图谱嵌入，Quaternion Knowledge Graph Embeddings

理解医学图像中的迁移学习，Transfusion: Understanding Transfer Learning for Medical Imaging

---

人工智能和机器学习领域的国际顶级会议NeurIPS 2019公布了接受论文，有效提交论文6743篇论文， 总共有1428接受论文, 21.1%接受率，包括36篇Oral，164篇Spotlights。

NeurIPS是人工智能和机器学习领域的国际顶级会议，由NIPS基金会负责运营。该会议全称为神经信息处理系统大会(Conference and Workshop on Neural Information Processing Systems，NIPS)，自1987年开始，每年的12月份，来自世界各地的从事AI和ML相关的专家学者和从业人士汇聚一堂。受其名称歧义带来的压力（部分原因是其首字母缩写具有「暧昧的内涵」，带有性别歧视的意义），2018年的会议名称改为NeurIPS 。

NeurIPS 2019将在12月8号加拿大温哥华会议中心举行。

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
Risto Vuorio (University of Michigan) · Shao-Hua Sun (University of Southern California) · Hexiang Hu (University of Southern California) · Joseph J Lim (University of Southern California)

ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Jiasen Lu (Georgia Tech) · Dhruv Batra (Georgia Tech / Facebook AI Research (FAIR)) · Devi Parikh (Georgia Tech / Facebook AI Research (FAIR)) · Stefan Lee (Georgia Institute of Technology)

Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers
Liwei Wu (University of California, Davis) · Shuqing Li (University of California, Davis) · Cho-Jui Hsieh (UCLA) · James Sharpnack (UC Davis)

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
JiaWang Bian (The University of Adelaide) · Zhichao Li (Tusimple) · Naiyan Wang (Hong Kong University of Science and Technology) · Huangying Zhan (The University of Adelaide) · Chunhua Shen (University of Adelaide) · Ming-Ming Cheng (Nankai University) · Ian Reid (University of Adelaide)

Zero-shot Learning via Simultaneous Generating and Learning
Hyeonwoo Yu (Seoul National University) · Beomhee Lee (Seoul National University)

Ask not what AI can do for you, but what AI should do: Towards a framework of task delegability
Brian Lubars (University of Colorado Boulder) · Chenhao Tan (University of Colorado Boulder)

Stand-Alone Self-Attention in Vision Models
Niki Parmar (Google) · Prajit Ramachandran (Google Brain) · Ashish Vaswani (Google Brain) · Irwan Bello (Google) · Anselm Levskaya (Google) · Jon Shlens (Google Research)

High Fidelity Video Prediction with Large Neural Nets
Ruben Villegas (Adobe Research / U. Michigan) · Arkanath Pathak (Google) · Harini Kannan (Google Brain) · Honglak Lee (Google / U. Michigan) · Dumitru Erhan (Google Brain) · Quoc V Le (Google)

Unsupervised learning of object structure and dynamics from videos
Matthias Minderer (Google Research) · Chen Sun (Google Research) · Ruben Villegas (Adobe Research / U. Michigan) · Forrester Cole (Google Research) · Kevin P Murphy (Google) · Honglak Lee (Google Brain)

TensorPipe: Easy Scaling with Micro-Batch Pipeline Parallelism
Yanping Huang (Google Brain) · Youlong Cheng (Google) · Ankur Bapna (Google) · Orhan Firat (Google) · Dehao Chen (Google) · Mia Chen (Google Brain) · HyoukJoong Lee (Google) · Jiquan Ngiam (Google Brain) · Quoc V Le (Google) · Yonghui Wu (Google) · zhifeng Chen (Google Brain)

Meta-Learning with Implicit Gradients
Aravind Rajeswaran (University of Washington) · Chelsea Finn (Stanford University) · Sham Kakade (University of Washington) · Sergey Levine (UC Berkeley)

Adversarial Examples Are Not Bugs, They Are Features
Andrew Ilyas (MIT) · Shibani Santurkar (MIT) · Dimitris Tsipras (MIT) · Logan Engstrom (MIT) · Brandon Tran (Massachusetts Institute of Technology) · Aleksander Madry (MIT)

Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
Vineet Kosaraju (Stanford University) · Amir Sadeghian (Stanford University) · Roberto Martín-Martín (Stanford University) · Ian Reid (University of Adelaide) · Hamid Rezatofighi (University of Adelaide) · Silvio Savarese (Stanford University)

FreeAnchor: Learning to Match Anchors for Visual Object Detection
Xiaosong Zhang (University of Chinese Academy of Sciences) · Fang Wan (University of Chinese Academy of Sciences) · Chang Liu (University of Chinese Academy of Sciences) · Rongrong Ji (Xiamen University, China) · Qixiang Ye (University of Chinese Academy of Sciences, China)

Differentially Private Hypothesis Selection
Mark Bun (Princeton University) · Gautam Kamath (University of Waterloo) · Thomas Steinke (IBM, Almaden) · Steven Wu (Microsoft Research)

New Differentially Private Algorithms for Learning Mixtures of Well-Separated Gaussians
Gautam Kamath (University of Waterloo) · Or Sheffet (University of Alberta) · Vikrant Singhal (Northeastern University) · Jonathan Ullman (Northeastern University)

Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation
Mark Bun (Princeton University) · Thomas Steinke (IBM, Almaden)

Multi-Resolution Weak Supervision for Sequential Data
Paroma Varma (Stanford University) · Frederic Sala (Stanford) · Shiori Sagawa (Stanford University) · Jason Fries (Stanford University) · Daniel Fu (Stanford University) · Saelig Khattar (Stanford University) · Ashwini Ramamoorthy (Stanford University) · Ke Xiao (Stanford University) · Kayvon Fatahalian (Stanford) · James Priest (Stanford University) · Christopher Ré (Stanford)

DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision
Tam Nguyen (Freiburg Computer Vision Lab) · Maximilian Dax (Bosch GmbH) · Chaithanya Kumar Mummadi (Robert Bosch GmbH) · Nhung Ngo (Bosch Center for Artificial Intelligence) · Thi Hoai Phuong Nguyen (KIT) · Zhongyu Lou (Robert Bosch Gmbh) · Thomas Brox (University of Freiburg)

The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection
Vladimir V. Kniaz (IEEE) · Vladimir Knyaz (State Research Institute of Aviation Systems) · Fabio Remondino ("Fondazione Bruno Kessler, Italy")

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
Dinghuai Zhang (Peking University) · Tianyuan Zhang (Peking University) · Yiping Lu (Peking University) · Zhanxing Zhu (Peking University) · Bin Dong (Peking University)

Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
Chao Yang (Tsinghua University) · Xiaojian Ma (University of California, Los Angeles) · Wenbing Huang (Tsinghua University) · Fuchun Sun (Tsinghua) · 刘 华平 (清华大学) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) · Chuang Gan (MIT-IBM Watson AI Lab)

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance
Kimia Nadjahi ( Télécom ParisTech) · Alain Durmus (ENS) · Umut Simsekli (Institut Polytechnique de Paris) · Roland Badeau (Télécom ParisTech)

Generalized Sliced Wasserstein Distances
Soheil Kolouri (HRL Laboratories LLC) · Kimia Nadjahi ( Télécom ParisTech) · Umut Simsekli (Institut Polytechnique de Paris) · Roland Badeau (Télécom ParisTech) · Gustavo Rohde (University of Virginia)

First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise
Than Huy Nguyen (Telecom ParisTech) · Umut Simsekli (Institut Polytechnique de Paris) · Mert Gurbuzbalaban (Rutgers) · Gaël RICHARD (Télécom ParisTech)

Blind Super-Resolution Kernel Estimation using an Internal-GAN
Yosef Bell Kligler (Weizmann Istitute of Science) · Assaf Shocher (Weizmann Institute of Science) · Michal Irani (The Weizmann Institute of Science)

Noise-tolerant fair classification
Alex Lamy (Columbia University) · Ziyuan Zhong (Columbia University) · Aditya Menon (Google) · Nakul Verma (Columbia University)

Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
Bingzhe Wu (Peeking University) · Shiwan Zhao (IBM Research - China) · Haoyang Xu (Peking University) · Chaochao Chen (Ant Financial) · Li Wang (Ant Financial) · Xiaolu Zhang (Ant Financial Services Group) · Guangyu Sun (Peking University) · Jun Zhou (Ant Financial)

Joint-task Self-supervised Learning for Temporal Correspondence
xueting li (uc merced) · Sifei Liu (NVIDIA) · Shalini De Mello (NVIDIA) · Xiaolong Wang (CMU) · Jan Kautz (NVIDIA) · Ming-Hsuan Yang (UC Merced / Google)

Provable Gradient Variance Guarantees for Black-Box Variational Inference
Justin Domke (University of Massachusetts, Amherst)

Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation
Justin Domke (University of Massachusetts, Amherst) · Daniel Sheldon (University of Massachusetts Amherst)

Experience Replay for Continual Learning
David Rolnick (UPenn) · Arun Ahuja (DeepMind) · Jonathan Schwarz (DeepMind) · Timothy Lillicrap (Google DeepMind) · Gregory Wayne (Google DeepMind)

Deep ReLU Networks Have Surprisingly Few Activation Patterns
Boris Hanin (Texas A&M) · David Rolnick (UPenn)

Chasing Ghosts: Instruction Following as Bayesian State Tracking
Peter Anderson (Georgia Tech) · Ayush Shrivastava (Georgia Institute of Technology) · Devi Parikh (Georgia Tech / Facebook AI Research (FAIR)) · Dhruv Batra (Georgia Tech / Facebook AI Research (FAIR)) · Stefan Lee (Georgia Institute of Technology)

Block Coordinate Regularization by Denoising
Yu Sun (Washington University in St. Louis) · Jiaming Liu (Washington University in St. Louis) · Ulugbek Kamilov (Washington University in St. Louis)

Reducing Noise in GAN Training with Variance Reduced Extragradient
Tatjana Chavdarova (Mila & Idiap & EPFL) · Gauthier Gidel (Mila) · François Fleuret (Idiap Research Institute) · Simon Lacoste-Julien (Mila, Université de Montréal)

Learning Erdos-Renyi Random Graphs via Edge Detecting Queries
Zihan Li (National University of Singapore) · Matthias Fresacher (University of Adelaide) · Jonathan Scarlett (National University of Singapore)

A Primal-Dual link between GANs and Autoencoders
Hisham Husain (The Australian National University) · Richard Nock (Data61, the Australian National University and the University of Sydney) · Robert Williamson (Australian National University & Data61)

muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking
CONGCHAO WANG (Virginia Tech) · Yizhi Wang (Virginia Tech) · Yinxue Wang (Virginia Tech) · Chiung-Ting Wu (Virginia Tech) · Guoqiang Yu (Virginia Tech)

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
Qiming Zhang (the University of Sydney) · Jing Zhang (The University of Sydney) · Wei Liu (Tencent AI Lab) · Dacheng Tao (University of Sydney)

Invert to Learn to Invert
Patrick Putzky (University of Amsterdam) · Max Welling (University of Amsterdam / Qualcomm AI Research)

Equitable Stable Matchings in Quadratic Time
Nikolaos Tziavelis (Northeastern University) · Ioannis Giannakopoulos (National Technical University of Athens) · Katerina Doka (NTUA) · Nectarios Koziris (NTUA) · Panagiotis Karras (Aarhus University)

Zero-Shot Semantic Segmentation
Maxime Bucher (Valeo.ai) · Tuan-Hung VU (Valeo.ai) · Matthieu Cord (Sorbonne University) · Patrick Pérez (Valeo.ai)

Metric Learning for Adversarial Robustness
Chengzhi Mao (Columbia University) · Ziyuan Zhong (Columbia University) · Junfeng Yang (Columbia University) · Carl Vondrick (Columbia University) · Baishakhi Ray (Columbia University)

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
Qiangeng Xu (USC) · Weiyue Wang (USC) · Duygu Ceylan (Adobe Research) · Radomir Mech (Adobe Systems Incorporated) · Ulrich Neumann (USC)

Batched Multi-armed Bandits Problem
Zijun Gao (Stanford University) · Yanjun Han (Stanford University) · Zhimei Ren (Stanford University) · Zhengqing Zhou (Stanford University)

vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
Fan-Yun Sun (National Taiwan University) · Meng Qu (MILA) · Jordan Hoffmann (Harvard University/Mila) · Chin-Wei Huang (MILA) · Jian Tang (HEC Montreal & MILA)

Differentially Private Bayesian Linear Regression
Garrett Bernstein (University of Massachusetts Amherst) · Daniel Sheldon (University of Massachusetts Amherst)

Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
Yitian Yuan (Tsinghua University) · Lin Ma (Tencent AI Lab) · Jingwen Wang (Tencent AI Lab) · Wei Liu (Tencent AI Lab) · Wenwu Zhu (Tsinghua University)

AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling
Bichuan Guo (Tsinghua University) · Yuxing Han (South China Agriculture University) · Jiangtao Wen (Tsinghua University)

CPM-Nets: Cross Partial Multi-View Networks
Changqing Zhang (Tianjin university) · Zongbo Han (Tianjin University) · yajie cui (tianjin university) · Huazhu Fu (Inception Institute of Artificial Intelligence) · Joey Tianyi Zhou (IHPC, A*STAR) · Qinghua Hu (Tianjin University)

Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
Xihui Liu (The Chinese University of Hong Kong) · Guojun Yin (University of Science and Technology of China) · Jing Shao (Sensetime) · Xiaogang Wang (The Chinese University of Hong Kong) · hongsheng Li (cuhk)

Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling
Andrey Kolobov (Microsoft Research) · Yuval Peres (N/A) · Cheng Lu (Microsoft) · Eric J Horvitz (Microsoft Research)

SySCD: A System-Aware Parallel Coordinate Descent Algorithm
Celestine Mendler-Dünner (UC Berkeley) · Nikolas Ioannou (IBM Research) · Thomas Parnell (IBM Research)

Importance Weighted Hierarchical Variational Inference
Artem Sobolev (Samsung) · Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow)

RSN: Randomized Subspace Newton
Robert Gower (Telecom-Paristech) · Dmitry Koralev (KAUST) · Felix Lieder (Heinrich-Heine-Universität Düsseldorf) · Peter Richtarik (KAUST)

Trust Region-Guided Proximal Policy Optimization
Yuhui Wang (Nanjing University of Aeronautics and Astronautics, China) · Hao He (Nanjing University of Aeronautics and Astronautics) · Xiaoyang Tan (Nanjing University of Aeronautics and Astronautics, China) · Yaozhong Gan (Nanjing University of Aeronautics and Astronautics, China)

Adversarial Self-Defense for Cycle-Consistent GANs
Dina Bashkirova (Boston University) · Ben Usman (Boston University) · Kate Saenko (Boston University)

Towards closing the gap between the theory and practice of SVRG
Othmane Sebbouh (Télécom ParisTech) · Nidham Gazagnadou (Télécom ParisTech) · Samy Jelassi (Princeton University) · Francis Bach (INRIA - Ecole Normale Superieure) · Robert Gower (Telecom-Paristech)

Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control
Armin Lederer (Technical University of Munich) · Jonas Umlauft (Technical University of Munich) · Sandra Hirche (Technische Universitaet Muenchen)

ETNet: Error Transition Network for Arbitrary Style Transfer
Chunjin Song (Shenzhen University) · Zhijie Wu (Shenzhen University) · Yang Zhou (Shenzhen University) · Minglun Gong (Memorial Univ) · Hui Huang (Shenzhen University)

No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms
Max Vladymyrov (Google)

Deep Equilibrium Models
Shaojie Bai (Carnegie Mellon University) · J. Zico Kolter (Carnegie Mellon University / Bosch Center for AI) · Vladlen Koltun (Intel Labs)

Saccader: Accurate, Interpretable Image Classification with Hard Attention
Gamaleldin Elsayed (Google Brain) · Simon Kornblith (Google Brain) · Quoc V Le (Google)

Multiway clustering via tensor block models 
Miaoyan Wang (University of Wisconsin - Madison) · Yuchen Zeng (University of Wisconsin - Madison)

Regret Minimization for Reinforcement Learning on Multi-Objective Online Markov Decision Processes
Wang Chi Cheung (Department of Industrial Systems Engineering and Management, National University of Singapore)

NAT: Neural Architecture Transformer for Accurate and Compact Architectures
Yong Guo (South China University of Technology) · Yin Zheng (Tencent AI Lab) · Mingkui Tan (South China University of Technology) · Qi Chen (South China University of Technology) · Jian Chen ("South China University of Technology, China") · Peilin Zhao (Tencent AI Lab) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)

Selecting Optimal Decisions via Distributionally Robust Nearest-Neighbor Regression
Ruidi Chen (Boston University) · Ioannis Paschalidis (Boston University)

Network Pruning via Transformable Architecture Search
Xuanyi Dong (University of Technology Sydney) · Yi Yang (UTS)

Differentiable Cloth Simulation for Inverse Problems
Junbang Liang (University of Maryland, College Park) · Ming Lin (UMD-CP & UNC-CH ) · Vladlen Koltun (Intel Labs)

Poisson-randomized Gamma Dynamical Systems
Aaron Schein (UMass Amherst) · Scott Linderman (Columbia University) · Mingyuan Zhou (University of Texas at Austin) · David Blei (Columbia University) · Hanna Wallach (MSR NYC)

Volumetric Correspondence Networks for Optical Flow
Gengshan Yang (Carnegie Mellon University) · Deva Ramanan (Carnegie Mellon University)

Learning Conditional Deformable Templates with Convolutional Networks
Adrian Dalca (MIT, HMS) · Marianne Rakic (ETH Zürich) · John Guttag (Massachusetts Institute of Technology) · Mert Sabuncu (Cornell)

Fast Low-rank Metric Learning for Large-scale and High-dimensional Data
Han Liu (Tsinghua University) · Zhizhong Han (University of Maryland, College Park) · Yu-Shen Liu (Tsinghua University) · Ming Gu (Tsinghua University)

Efficient Symmetric Norm Regression via Linear Sketching
Zhao Song (University of Washington) · Ruosong Wang (Carnegie Mellon University) · Lin Yang (Johns Hopkins University) · Hongyang Zhang (Carnegie Mellon University) · Peilin Zhong (Columbia University)

RUBi: Reducing Unimodal Biases in Visual Question Answering
Remi Cadene (LIP6) · Corentin Dancette (LIP6) · Hedi Ben younes (Université Pierre & Marie Curie / Heuritech) · Matthieu Cord (Sorbonne University) · Devi Parikh (Georgia Tech / Facebook AI Research (FAIR))

Reducing Scene Bias of Convolutional Neural Networks for Human Action Understanding
Jinwoo Choi (Virginia Tech) · Chen Gao (Virginia Tech) · Joseph C.E. Messou (Virginia Tech) · Jia-Bin Huang (Virginia Tech)

NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
Yichao Zhou (UC Berkeley) · Haozhi Qi (UC Berkeley) · Jingwei Huang (Stanford University) · Yi Ma (UC Berkeley)

DATA: Differentiable ArchiTecture Approximation
Jianlong Chang (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences) · xinbang zhang (Institute of Automation,Chinese Academy of Science) · Yiwen Guo (Intel Labs China) · GAOFENG MENG (Institute of Automation, Chinese Academy of Sciences) · SHIMING XIANG (Chinese Academy of Sciences, China) · Chunhong Pan (Institute of Automation, Chinese Academy of Sciences)

Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Tingting Qiao (Zhejiang University) · Jing Zhang (The University of Sydney) · Duanqing Xu (Zhejiang University) · Dacheng Tao (University of Sydney)

Memory-oriented Decoder for Light Field Salient Object Detection
Miao Zhang (Dalian University of Technology) · Jingjing Li (Dalian University of Technology) · Wei Ji (Dalian University of Technology) · Yongri Piao (Dalian University of Technology) · Huchuan Lu (Dalian University of Technology)

Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition
Xuesong Niu (Institute of Computing Technology, CAS) · Hu Han (ICT, CAS) · Shiguang Shan (Chinese Academy of Sciences) · Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels
Natalia Neverova (Facebook AI Research) · David Novotny (Facebook AI Research) · Andrea Vedaldi (University of Oxford / Facebook AI Research)

Powerset Convolutional Neural Networks
Chris Wendler (ETH Zurich) · Markus Püschel (ETH Zurich) · Dan Alistarh (IST Austria)

Optimal Pricing in Repeated Posted-Price Auctions with Different Patience of the Seller and the Buyer
Arsenii Vanunts (Yandex) · Alexey Drutsa (Yandex)

An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums
Hadrien Hendrikx (INRIA) · Francis Bach (INRIA - Ecole Normale Superieure) · Laurent Massoulié (Inria)

Efficient 3D Deep Learning via Point-Based Representation and Voxel-Based Convolution
Zhijian Liu (MIT) · Haotian Tang (Shanghai Jiao Tong University) · Yujun Lin (MIT) · Song Han (MIT)

Deep Learning without Weight Transport
Mohamed Akrout (University of Toronto) · Collin Wilson (University of Toronto) · Peter Humphreys (Google) · Timothy Lillicrap (Google DeepMind) · Douglas Tweed (University of Toronto)

Combinatorial Bandits with Relative Feedback 
Aadirupa Saha (Indian Institute of SCience) · Aditya Gopalan (Indian Institute of Science)

General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme
Tao Sun (National university of defense technology) · Yuejiao Sun (University of California, Los Angeles) · Dongsheng Li (School of Computer Science, National University of Defense Technology) · Qing Liao (Harbin Institute of Technology (Shenzhen))

Joint Optimizing of Cycle-Consistent Networks
Leonidas J Guibas (stanford.edu) · Qixing Huang (The University of Texas at Austin) · Zhenxiao Liang (The University of Texas at Austin)

Explicit Disentanglement of Appearance and Perspective in Generative Models
Nicki Skafte Detlefsen (Technical University of Denmark) · Søren Hauberg (Technical University of Denmark)

Polynomial Cost of Adaptation for X-Armed Bandits
Hedi Hadiji (Laboratoire de Mathematiques d’Orsay, Univ. Paris-Sud,)

Learning to Propagate for Graph Meta-Learning
LU LIU (University of Technology Sydney) · Tianyi Zhou (University of Washington, Seattle) · Guodong Long (University of Technology Sydney) · Jing Jiang (University of Technology Sydney) · Chengqi Zhang (University of Technology Sydney)

Secretary Ranking with Minimal Inversions
Sepehr Assadi (Princeton University) · Eric Balkanski (Harvard University) · Renato Leme (Google Research)

Nonparametric Regressive Point Processes Based on Conditional Gaussian Processes
Siqi Liu (University of Pittsburgh) · Milos Hauskrecht (University of Pittsburgh)

Learning Perceptual Inference by Contrasting
Chi Zhang (University of California, Los Angeles) · Baoxiong Jia (UCLA) · Feng Gao (UCLA) · Yixin Zhu (University of California, Los Angeles) · HongJing Lu (UCLA) · Song-Chun Zhu (UCLA)

Selecting the independent coordinates of manifolds with large aspect ratios
Yu-Chia Chen (University of Washington) · Marina Meila (University of Washington)

Region-specific Diffeomorphic Metric Mapping
Zhengyang Shen (University of North Carolina at Chapel Hill) · Francois-Xavier Vialard (University Paris-Est) · Marc Niethammer (UNC Chapel Hill)

Subset Selection via Supervised Facility Location
Chengguang Xu (Northeastern University) · Ehsan Elhamifar (Northeastern University)

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
Vincent Sitzmann (Stanford University) · Michael Zollhoefer (Stanford University) · Gordon Wetzstein (Stanford University)

Reconciling λ-Returns with Experience Replay
Brett Daley (Northeastern University) · Christopher Amato (Northeastern University)

Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence
Fengxiang He (The University of Sydney) · Tongliang Liu (The University of Sydney) · Dacheng Tao (University of Sydney)

Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
Max Simchowitz (Berkeley) · Kevin Jamieson (U Washington)

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation
Mitsuru Kusumoto (Preferred Networks, Inc.) · Takuya Inoue (University of Tokyo) · Gentaro Watanabe (Preferred Networks, Inc.) · Takuya Akiba (Preferred Networks, Inc.) · Masanori Koyama (Preferred Networks Inc. )

Combinatorial Inference against Label Noise
Paul Hongsuck Seo (POSTECH) · Geeho Kim (Seoul National University) · Bohyung Han (Seoul National University)

Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
Chao Qu (Ant Financial Services Group) · Shie Mannor (Technion) · Huan Xu (Georgia Inst. of Technology) · Yuan Qi (Ant Financial Services Group) · Le Song (Ant Financial Services Group) · Junwu Xiong (Ant Financial Services Group)

Convolution with even-sized kernels and symmetric padding
Shuang Wu (Tsinghua University) · Guanrui Wang (Tsinghua University) · Pei Tang (Tsinghua University) · Feng Chen (Tsinghua University) · Luping Shi (tsinghua university)

On The Classification-Distortion-Perception Tradeoff
Dong Liu (University of Science and Technology of China) · Haochen Zhang (University of Science and Technology of China) · Zhiwei Xiong (University of Science and Technology of China)

Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up
Dominic Richards (University of Oxford) · Patrick Rebeschini (University of Oxford)

Online sampling from log-concave distributions
Holden Lee (Princeton University) · Oren Mangoubi (EPFL) · Nisheeth Vishnoi (Yale University)

Envy-Free Classification
Maria-Florina Balcan (Carnegie Mellon University) · Travis Dick (Carnegie Mellon University) · Ritesh Noothigattu (Carnegie Mellon University) · Ariel D Procaccia (Carnegie Mellon University)

Finding Friend and Foe in Multi-Agent Games
Jack S Serrino (MIT) · Max Kleiman-Weiner (Harvard) · David Parkes (Harvard University) · Josh Tenenbaum (MIT)

Computer Vision with a Single (Robust) Classifier
Shibani Santurkar (MIT) · Andrew Ilyas (MIT) · Dimitris Tsipras (MIT) · Logan Engstrom (MIT) · Brandon Tran (Massachusetts Institute of Technology) · Aleksander Madry (MIT)

Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
Anton Obukhov (ETH Zurich) · Stamatios Georgoulis (ETH Zurich) · Dengxin Dai (ETH Zurich) · Luc V Gool (Computer Vision Lab, ETH Zurich)

Model Compression with Adversarial Robustness: A Unified Optimization Framework
Shupeng Gui (University of Rochester) · Haotao N Wang (Texas A&M University) · Haichuan Yang (University of Rochester) · Chen Yu (University of Rochester) · Zhangyang Wang (TAMU) · Ji Liu (University of Rochester, Tencent AI lab)

Neuron Communication Networks
Jianwei Yang (Georgia Tech) · Zhile Ren (Georgia Tech) · Chuang Gan (MIT-IBM Watson AI Lab) · Hongyuan Zhu (Astar) · Ji Lin (MIT) · Devi Parikh (Georgia Tech / Facebook AI Research (FAIR))

CondConv: Conditionally Parameterized Convolutions for Efficient Inference
Brandon Yang (Google Brain) · Gabriel Bender (Google Brain) · Quoc V Le (Google) · Jiquan Ngiam (Google Brain)

Regression Planning Networks
Danfei Xu (Stanford University) · Roberto Martín-Martín (Stanford University) · De-An Huang (Stanford University) · Yuke Zhu (Stanford University) · Silvio Savarese (Stanford University) · Li Fei-Fei (Stanford University)

Twin Auxilary Classifiers GAN
Mingming Gong (University of Melbourne) · Yanwu Xu (University of Pittsburgh) · Chunyuan Li (Microsoft Research) · Kun Zhang (CMU) · Kayhan Batmanghelich (University of Pittsburgh)

Conditional Structure Generation through Graph Variational Generative Adversarial Nets
Carl Yang (University of Illinois, Urbana Champaign) · Peiye Zhuang (UIUC) · Wenhan Shi (UIUC) · Alan Luu (UIUC) · Pan Li (Stanford)

Distributional Policy Optimization: An Alternative Approach for Continuous Control
Chen Tessler (Technion) · Guy Tennenholtz (Technion) · Shie Mannor (Technion)

Sampling Sketches for Concave Sublinear Functions of Frequencies
Edith Cohen (Google) · Ofir Geri (Stanford University)

Deliberative Explanations: visualizing network insecurities
Pei Wang (UC San Diego) · Nuno Nvasconcelos (UC San Diego)

Computing Full Conformal Prediction Set with Approximate Homotopy
Eugene Ndiaye (Riken AIP) · Ichiro Takeuchi (Nagoya Institute of Technology)

Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
Stephan Rabanser (Amazon) · Stephan Günnemann (Technical University of Munich) · Zachary Lipton (Carnegie Mellon University)

Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards
Siyuan Li (Tsinghua University) · Rui Wang (Tsinghua University) · Minxue Tang (Tsinghua University) · Chongjie Zhang (Tsinghua University)

Multi-View Reinforcement Learning
Minne Li (University College London) · Lisheng Wu (UCL) · Jun WANG (UCL)

Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
Thang Vu (KAIST) · Hyunjun Jang (KAIST) · Trung Pham (KAIST) · Chang Yoo (KAIST)

Neural Diffusion Distance for Image Segmentation
Jian Sun (Xi'an Jiaotong University) · Zongben Xu (XJTU)

Fine-grained Optimization of Deep Neural Networks
Mete Ozay (Independent Researcher (N/A))

Extending Stein’s Unbiased Risk Estimator To Train Deep Denoisers with Correlated Pairs of Noisy Images
Magauiya Zhussip (UNIST) · Shakarim Soltanayev (Ulsan National Institute of Science and Technology) · Se Young Chun (UNIST)

Wibergian Learning of Continuous Energy Functions
Chris Russell (The Alan Turing Institute/ The University of Surrey) · Matteo Toso (University of Surrey) · Neill Campbell (University of Bath)

Hyperspherical Prototype Networks
Pascal Mettes (University of Amsterdam) · Elise van der Pol (University of Amsterdam) · Cees Snoek (University of Amsterdam)

Expressive power of tensor-network factorizations for probabilistic modelling
Ivan Glasser (Max Planck Institute of Quantum Optics) · Ryan Sweke (Freie Universitaet Berlin) · Nicola Pancotti (Max Planck Institute of Quantum Optics) · Jens Eisert (Freie Universitaet Berlin) · Ignacio Cirac (Max-Planck Institute of Quantum Optics)

HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs
Naganand Yadati (Indian Institute of Science) · Madhav Nimishakavi (Indian Institute of Science) · Prateek Yadav (Indian Institute of Science) · Vikram Nitin (Indian Institute of Science) · Anand Louis (Indian Institute of Science, Bangalore, India) · Partha Talukdar (Indian Institute of Science, Bangalore)

SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points
Zhize Li (Tsinghua University)

Efficient Meta Learning via Minibatch Proximal Update
Pan Zhou (National University of Singapore) · Xiaotong Yuan (Nanjing University of Information Science & Technology) · Huan Xu (Alibaba Group) · Shuicheng Yan (National University of Singapore) · Jiashi Feng (National University of Singapore)

Unconstrained Monotonic Neural Networks
Antoine Wehenkel (ULiège) · Gilles Louppe (University of Liège)

Guided Similarity Separation for Image Retrieval
Chundi Liu (Layer6 AI) · Guangwei Yu (Layer6) · Maksims Volkovs (layer6.ai) · Cheng Chang (Layer6 AI) · Himanshu Rai (Layer6 AI) · Junwei Ma (Layer6 AI) · Satya Krishna Gorti (Layer6 AI)

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Kaidi Cao (Stanford University) · Colin Wei (Stanford University) · Adrien Gaidon (Toyota Research Institute) · Nikos Arechiga (Toyota Research Institute) · Tengyu Ma (Stanford)

Strategizing against No-regret Learners
Yuan Deng (Duke University) · Jon Schneider (Google Research) · Balasubramanian Sivan (Google Research)

D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
Muhan Zhang (Washington University in St. Louis) · Shali Jiang (Washington University in St. Louis) · Zhicheng Cui (Washington University in St. Louis) · Roman Garnett (Washington University in St. Louis) · Yixin Chen (Washington University in St. Louis)

Hierarchical Optimal Transport for Document Representation
Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab) · Sebastian Claici (MIT) · Edward Chien (Massachusetts Institute of Technology) · Farzaneh Mirzazadeh (IBM Research, MIT-IBM Watson AI Lab) · Justin M Solomon (MIT)

Multivariate Sparse Coding of Nonstationary Covariances with Gaussian Processes
Rui Li (Rochester Institute of Technology)

Positional Normalization
Boyi Li (Cornell University) · Felix Wu (Cornell University) · Kilian Weinberger (Cornell University) · Serge Belongie (Cornell University)

A New Defense Against Adversarial Images: Turning a Weakness into a Strength
Shengyuan Hu (Cornell University) · Tao Yu (Cornell University) · Chuan Guo (Cornell University) · Wei-Lun Chao (Cornell University Ohio State University (OSU)) · Kilian Weinberger (Cornell University)

Quadratic Video Interpolation
Xiangyu Xu (Tsinghua University) · Li Si-Yao (Beijing Normal University) · Wenxiu Sun (SenseTime Research) · Qian Yin (Beijing Normal University) · Ming-Hsuan Yang (UC Merced / Google)

ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies
Bao Wang (UCLA) · Zuoqiang Shi (zqshi@mail.tsinghua.edu.cn) · Stanley Osher (UCLA)

Incremental Scene Synthesis
Benjamin Planche (Siemens Corporate Technology) · Xuejian Rong (City University of New York) · Ziyan Wu (Siemens Corporation) · Srikrishna Karanam (Siemens Corporate Technology, Princeton) · Harald Kosch (PASSAU) · YingLi Tian (City University of New York) · Jan Ernst (Siemens Research) · ANDREAS HUTTER (Siemens Corporate Technology, Germany)

Self-Supervised Generalisation with Meta Auxiliary Learning
Shikun Liu (Imperial College London) · Andrew Davison (Imperial College London) · Edward Johns (Imperial College London)

Variational Denoising Network: Toward Blind Noise Modeling and Removal
Zongsheng Yue (Xi'an Jiaotong University) · Hongwei Yong (The Hong Kong Polytechnic University) · Qian Zhao (Xi'an Jiaotong University) · Deyu Meng (Xi'an Jiaotong University) · Lei Zhang (The Hong Kong Polytechnic Univ)

Fast Sparse Group Lasso
Yasutoshi Ida (NTT) · Yasuhiro Fujiwara (NTT Software Innovation Center) · Hisashi Kashima (Kyoto University/RIKEN Center for AIP)

Learnable Tree Filter for Structure-preserving Feature Transform
Lin Song (Xi'an Jiaotong University) · Yanwei Li (Institute of Automation, Chinese Academy of Sciences) · Zeming Li (Megvii(Face++) Inc) · Gang Yu (Megvii Inc) · Hongbin Sun (Xi'an Jiaotong University) · Jian Sun (Megvii, Face++) · Nanning Zheng (Xi'an Jiaotong University)

Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis
Yuki Yoshida (The University of Tokyo) · Masato Okada (The University of Tokyo)

Coordinated hippocampal-entorhinal replay as structural inference
Talfan Evans (University College London) · Neil Burgess (University College London)

Cascaded Dilated Dense Network with Two-step Data Consistency for MRI Reconstruction
Hao Zheng (East China Normal University) · Faming Fang (East China Normal University) · Guixu Zhang (East China Normal University)

On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
Aaron Defazio (Facebook AI Research) · Leon Bottou (FAIR)

On the Curved Geometry of Accelerated Optimization
Aaron Defazio (Facebook AI Research)

Multi-marginal Wasserstein GAN
Jiezhang Cao (South China University of Technology) · Langyuan Mo (South China University of Technology) · Yifan Zhang (South China University of Technology) · Kui Jia (South China University of Technology) · Chunhua Shen (University of Adelaide) · Mingkui Tan (South China University of Technology)

Better Exploration with Optimistic Actor Critic
Kamil Ciosek (Microsoft) · Quan Vuong (University of California San Diego) · Robert Loftin (Microsoft Research) · Katja Hofmann (Microsoft Research)

Importance Resampling for Off-policy Prediction
Matthew Schlegel (University of Alberta) · Wesley Chung (University of Alberta) · Daniel Graves (Huawei) · Jian Qian (University of Alberta) · Martha White (University of Alberta)

The Label Complexity of Active Learning from Observational Data
Songbai Yan (University of California, San Diego) · Kamalika Chaudhuri (UCSD) · Tara Javidi (University of California San Diego)

Meta-Learning Representations for Continual Learning
Khurram Javed (University of Alberta) · Martha White (University of Alberta)

Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Haichao Zhang (Horizon Robotics) · Jianyu Wang (Baidu USA)

Visualizing the PHATE of Neural Networks
Scott Gigante (Yale University) · Adam S Charles (Princeton University) · Smita Krishnaswamy (Yale University) · Gal Mishne (Yale)

The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers
Alex X Lu (University of Toronto) · Amy X Lu (University of Toronto/Vector Institute) · Wiebke Schormann (Sunnybrook Research Institute) · David Andrews (Sunnybrook Research Institute) · Alan Moses (University of Toronto)

Nonconvex Low-Rank Tensor Completion from Noisy Data
Changxiao Cai (Princeton University) · Gen Li (Tsinghua University) · H. Vincent Poor (Princeton University) · Yuxin Chen (Princeton University)

Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization
Gautam Goel (Caltech) · Yiheng Lin (Institute for Interdisciplinary Information Sciences, Tsinghua University) · Haoyuan Sun (California Institute of Technology) · Adam Wierman (California Institute of Technology)

Channel Gating Neural Networks
Weizhe Hua (Cornell University) · Yuan Zhou (Cornell) · Christopher De Sa (Cornell) · Zhiru Zhang (Cornell Univeristy) · G. Edward Suh (Cornell University)

Neural networks grown and self-organized by noise
Guruprasad Raghavan (California Institute of Technology) · Matt Thomson (California Institute of Technology)

Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
Xinyang Chen (Tsinghua University) · Sinan Wang (Tsinghua University) · Bo Fu (Tsinghua University) · Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University)

Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
Jun Shu (Xi'an Jiaotong University) · Qi Xie (Xi'an Jiaotong University) · Lixuan Yi (Xi'an Jiaotong University) · Qian Zhao (Xi'an Jiaotong University) · Sanping Zhou (Xi'an Jiaotong University) · Zongben Xu (Xi'an Jiaotong University) · Deyu Meng (Xi'an Jiaotong University)

Variational Structured Semantic Inference for Diverse Image Captioning
Fuhai Chen (Xiamen University) · Rongrong Ji (Xiamen University, China) · Jiayi Ji (Xiamen University) · Xiaoshuai Sun (Xiamen University) · Baochang Zhang (Beihang University) · Xuri Ge (Xiamen University) · Yongjian Wu (Tencent Technology (Shanghai) Co.,Ltd) · Feiyue Huang (Tencent) · Yan Wang (Microsoft)

Mapping State Space using Landmarks for Universal Goal Reaching
Zhiao Huang (University of California San Diego) · Hao Su (University of California San Diego) · Fangchen Liu (UCSD)

Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
Ximei Wang (Tsinghua University) · Ying Jin (Tsinghua University) · Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University) · Michael Jordan (UC Berkeley)

Random deep neural networks are biased towards simple functions
Giacomo De Palma (Massachusetts Institute of Technology) · Bobak Kiani (Massachusetts Institute of Technology) · Seth Lloyd (MIT)

XNAS: Neural Architecture Search with Expert Advice
Niv Nayman (Alibaba Group) · Asaf Noy (Alibaba) · Tal Ridnik (MIIL Alibaba) · Itamar Friedman (Alibaba) · Jing Rong (Alibaba) · Lihi Zelnik (Alibaba)

CNN^{2}: Viewpoint Generalization via a Binocular Vision
Wei-Da Chen (National Tsing Hua University) · Shan-Hung Wu (National Tsing Hua University)

Generalized Off-Policy Actor-Critic
Shangtong Zhang (University of Oxford) · Wendelin Boehmer (University of Oxford) · Shimon Whiteson (University of Oxford)

DAC: The Double Actor-Critic Architecture for Learning Options
Shangtong Zhang (University of Oxford) · Shimon Whiteson (University of Oxford)

Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models
Tao Yu (Cornell University) · Christopher De Sa (Cornell)

Controlling Neural Level Sets
Matan Atzmon (Weizmann Institute Of Science) · Niv Haim (Weizmann Institute of Science) · Lior Yariv (Weizmann Institute of Science) · Ofer Israelov (Weizmann Institute of Science) · Haggai Maron (Weizmann Institute, Israel) · Yaron Lipman (Weizmann Institute of Science)

Blended Matching Pursuit
Cyrille Combettes (Georgia Institute of Technology) · Sebastian Pokutta (Georgia Institute of Technology)

An Improved Analysis of Training Over-parameterized Deep Neural Networks
Difan Zou (University of California, Los Angeles) · Quanquan Gu (UCLA)

Controllable Text to Image Generation
Bowen Li (University of Oxford) · Xiaojuan Qi (University of Oxford) · Thomas Lukasiewicz (University of Oxford) · Philip Torr (University of Oxford)

Improving Textual Network Learning with Variational Homophilic Embeddings
Wenlin Wang (Duke Univeristy) · Chenyang Tao (Duke University) · Zhe Gan (Microsoft) · Guoyin Wang (Duke University) · Liqun Chen (Duke University) · Xinyuan Zhang (Duke University) · Ruiyi Zhang (Duke University) · Qian Yang (Duke University) · Ricardo Henao (Duke University) · Lawrence Carin (Duke University)

Rethinking Generative Coverage: A Pointwise Guaranteed Approach
Peilin Zhong (Columbia University) · Yuchen Mo (Columbia University) · Chang Xiao (Columbia University) · Pengyu Chen (Columbia University) · Changxi Zheng (Columbia University)

The Randomized Midpoint Method for Log-Concave Sampling
Ruoqi Shen (University of Washington) · Yin Tat Lee (UW)

Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update
Su Young Lee (KAIST) · Choi Sungik (KAIST) · Sae-Young Chung (KAIST)

Fully Neural Network based Model for General Temporal Point Processes
Takahiro Omi (The University of Tokyo) · naonori ueda (RIKEN AIP) · Kazuyuki Aihara (The University of Tokyo)

Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks
Zhonghui You (Peking University) · Kun Yan (Peking University) · Jinmian Ye (SMILE Lab) · Meng Ma (Peking University) · Ping Wang (Peking University)

Discrimination in Online Markets: Effects of Social Bias on Learning from Reviews and Policy Design
Faidra Monachou (Stanford University) · Itai Ashlagi (Stanford)

Provably Powerful Graph Networks
Haggai Maron (Weizmann Institute, Israel) · Heli Ben-Hamu (Weizmann Institute of Science) · Hadar Serviansky (WEIZMANN INSTITUTE OF SCIENCE) · Yaron Lipman (Weizmann Institute of Science)

Order Optimal One-Shot Distributed Learning
Arsalan Sharifnassab (Sharif University of Technology) · Saber Salehkaleybar (Sharif University of Technology) · S. Jamaloddin Golestani (Sharif University of Technology)

Information Competing Process for Learning Diversified Representations
Jie Hu (Xiamen University) · Rongrong Ji (Xiamen University, China) · ShengChuan Zhang (Xiamen University) · Xiaoshuai Sun (Xiamen University) · Qixiang Ye (University of Chinese Academy of Sciences, China) · Chia-Wen Lin (National Tsing Hua University) · Qi Tian (Huawei Noah’s Ark Lab)

GENO -- GENeric Optimization for Classical Machine Learning
Soeren Laue (Friedrich Schiller University Jena / Data Assessment Solutions) · Matthias Mitterreiter (Friedrich Schiller University Jena) · Joachim Giesen (Friedrich-Schiller-Universitat Jena)

Conditional Independence Testing using Generative Adversarial Networks
Alexis Bellot (University of Cambridge) · Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)

Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function
Aviv Rosenberg (Tel Aviv University) · Yishay Mansour (Tel Aviv University / Google)

Partitioning Structure Learning for Segmented Linear Regression Trees
Xiangyu Zheng (Peking University) · Song Xi Chen (Peking University)

A Tensorized Transformer for Language Modeling
Xindian Ma (Tianjin University) · Peng Zhang (Tianjin University) · Shuai Zhang (Tianjin University) · Nan Duan (Microsoft Research) · Yuexian Hou (Tianjin University) · Ming Zhou (Microsoft Research) · Dawei Song (Beijing Institute of Technology)

Kernel Stein Tests for Multiple Model Comparison
Jen Ning Lim (Max Planck Institute for Intelligent Systems) · Makoto Yamada (Kyoto University / RIKEN AIP) · Bernhard Schölkopf (MPI for Intelligent Systems) · Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems)

Disentangled behavioural representations
Amir Dezfouli (Data61, CSIRO) · Hassan Ashtiani (McMaster University) · Omar Ghattas (CSIRO) · Richard Nock (Data61, the Australian National University and the University of Sydney) · Peter Dayan (Max Planck Institute for Biological Cybernetics) · Cheng Soon Ong (Data61 and ANU)

More Is Less: Learning Efficient Video Representations by Temporal Aggregation Module
Quanfu Fan (IBM Research) · Chun-Fu Chen (IBM Research) · Hilde Kuehne (University of Bonn) · Marco Pistoia (IBM Research) · David Cox (MIT-IBM Watson AI Lab)

Rethinking the CSC Model for Natural Images
Dror Simon (Technion) · Michael Elad (Technion)

Integrating Generative and Discriminative Sparse Kernel Machines for Multi-class Active Learning
Weishi Shi (Rochester Institute of Technology) · Qi Yu (Rochester Institute of Technology)

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Deepak Pathak (UC Berkeley) · Christopher Lu (UC Berkeley) · Trevor Darrell (UC Berkeley) · Phillip Isola (Massachusetts Institute of Technology) · Alexei Efros (UC Berkeley)

Perceiving the arrow of time in autoregressive motion
Kristof Meding (Max Planck Institute for Intelligent Systems) · Dominik Janzing (Amazon) · Bernhard Schölkopf (MPI for Intelligent Systems) · Felix A. Wichmann (University of Tübingen)

DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
Ofir Nachum (Google Brain) · Yinlam Chow (DeepMind) · Bo Dai (Google Brain) · Lihong Li (Google Brain)

Hyper-Graph-Network Decoders for Block Codes
Eliya Nachmani (Tel Aviv University and Facebook AI Research) · Lior Wolf (Facebook AI Research)

Large Scale Markov Decision Processes with Changing Rewards
Adrian Rivera Cardoso (Georgia Tech) · He Wang (Georgia Institute of Technology) · Huan Xu (Georgia Inst. of Technology)

Multiview Aggregation for Learning Category-Specific Shape Reconstruction
Srinath Sridhar (Stanford University) · Davis Rempe (Stanford University) · Julien Valentin (Google) · Bouaziz Sofien () · Leonidas J Guibas (stanford.edu)

Semi-Parametric Dynamic Contextual Pricing
Virag Shah (Stanford) · Ramesh Johari (Stanford University) · Jose Blanchet (Stanford University)

Nearly Linear-Time, Deterministic Algorithm for Maximizing (Non-Monotone) Submodular Functions Under Cardinality Constraint
Alan Kuhnle (Florida State University)

Initialization of ReLUs for Dynamical Isometry
Rebekka Burkholz (Harvard University) · Alina Dubatovka (ETH Zurich)

Gradient Information for Representation and Modeling
Jie Ding (University of Minnesota) · Robert Calderbank (Duke University) · Vahid Tarokh (Duke University)

SpiderBoost and Momentum: Faster Variance Reduction Algorithms
Zhe Wang (Ohio State University) · Kaiyi Ji (The Ohio State University) · Yi Zhou (University of Utah) · Yingbin Liang (The Ohio State University) · Vahid Tarokh (Duke University)

Minimax rates of estimating approximate differential privacy
Xiyang Liu (University of Washington) · Sewoong Oh (University of Washington)

Backprop with Approximate Activations for Memory-efficient Network Training
Ayan Chakrabarti (Washington University in St. Louis) · Benjamin Moseley (Carnegie Mellon University)

Training Image Estimators without Image Ground Truth
Zhihao Xia (Washington University in St. Louis) · Ayan Chakrabarti (Washington University in St. Louis)

Deep Structured Prediction for Facial Landmark Detection
Lisha Chen (Rensselaer Polytechnic Institute) · Hui Su (IBM) · Qiang Ji (Rensselaer Polytechnic Institute)

Information-Theoretic Confidence Bounds for Reinforcement Learning
Xiuyuan Lu (Stanford University) · Benjamin Van Roy (Stanford University)

Transfer Anomaly Detection by Inferring Latent Domain Representations
Atsutoshi Kumagai (NTT) · Tomoharu Iwata (NTT) · Yasuhiro Fujiwara (NTT Software Innovation Center)

Total Least Squares Regression in Input Sparsity Time
Huaian Diao (Northeast Normal University) · Zhao Song (Harvard University & University of Washington) · David Woodruff (Carnegie Mellon University) · Xin Yang (University of Washington)

Park: An Open Platform for Learning-Augmented Computer Systems
Hongzi Mao (MIT) · Parimarjan Negi (MIT CSAIL) · Akshay Narayan (MIT CSAIL) · Hanrui Wang (Massachusetts Institute of Technology) · Jiacheng Yang (MIT CSAIL) · Haonan Wang (MIT CSAIL) · Ryan Marcus (MIT CSAIL) · ravichandra addanki (Massachusetts Institute of Technology) · Mehrdad Khani Shirkoohi (MIT) · Songtao He (Massachusetts Institute of Technology) · Vikram Nathan (MIT) · Frank Cangialosi (MIT CSAIL) · Shaileshh Venkatakrishnan (MIT) · Wei-Hung Weng (Massachusetts Institute of Technology) · Song Han (MIT) · Tim Kraska (MIT) · Dr.Mohammad Alizadeh (Massachusetts institute of technology)

Adapting Neural Networks for the Estimation of Treatment Effects
Claudia Shi (Columbia University) · David Blei (Columbia University) · Victor Veitch (Columbia University)

Learning Transferable Graph Exploration
Hanjun Dai (Georgia Tech) · Yujia Li (DeepMind) · Chenglong Wang (University of Washington) · Rishabh Singh (Google Brain) · Po-Sen Huang (DeepMind) · Pushmeet Kohli (DeepMind)

Conformal Prediction Under Covariate Shift
Rina Foygel Barber (University of Chicago) · Emmanuel Candes (Stanford University) · Aaditya Ramdas (CMU) · Ryan Tibshirani (Carnegie Mellon University)

Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation
Chen Dan (Carnegie Mellon University) · Hong Wang (Massachusetts Institute of Technology) · Hongyang Zhang (Carnegie Mellon University) · Yuchen Zhou (University of Wisconsin, Madison) · Pradeep Ravikumar (Carnegie Mellon University)

Asymmetric Valleys: Beyond Sharp and Flat Local Minima
Haowei He (Beihang University) · Gao Huang (Tsinghua) · Yang Yuan (Cornell University)

Positive-Unlabeled Compression on the Cloud
Yixing Xu (Huawei Noah's Ark Lab) · Yunhe Wang (Noah’s Ark Laboratory, Huawei Technologies Co., Ltd.) · Hanting Chen (Peking University) · Kai Han (Huawei Noah's Ark Lab) · Chunjing XU (Huawei Technologies) · Dacheng Tao (University of Sydney) · Chang Xu (University of Sydney)

Direct Estimation of Differential Functional Graphical Model
Boxin Zhao (UChicago) · Sam Wang (UW) · Mladen Kolar (University of Chicago)

On the Calibration of Multiclass Classification with Rejection
Chenri Ni (The University of Tokyo) · Nontawat Charoenphakdee (The University of Tokyo / RIKEN) · Junya Honda (The University of Tokyo / RIKEN) · Masashi Sugiyama (RIKEN / University of Tokyo)

Third-Person Visual Imitation Learning via Decoupled Hierarchical Control
Pratyusha Sharma (Carnegie Mellon University) · Deepak Pathak (UC Berkeley) · Abhinav Gupta (Facebook AI Research/CMU)

Stagewise Training Accelerates Convergence of Testing Error Over SGD
Zhuoning Yuan (UI-Computer Science) · Yan Yan (the University of Iowa) · Jing Rong (Alibaba) · Tianbao Yang (The University of Iowa)

Learning Robust Options by Conditional Value at Risk Optimization
Takuya Hiraoka (NEC) · Takahisa Imagawa (National Institute of Advanced Industrial Science and Technology) · Tatsuya Mori (NEC) · Takashi Onishi (NEC) · Yoshimasa Tsuruoka (The University of Tokyo)

Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems
Yi Xu (The University of Iowa) · Jing Rong (Alibaba) · Tianbao Yang (The University of Iowa)

On Learning Over-parameterized Neural Networks: A Functional Approximation Prospective
Lili Su (MIT) · Pengkun Yang (Princeton University)

Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries
Fuwen Tan (University of Virginia) · Paola Cascante-Bonilla (University of Virginia) · Xiaoxiao Guo (IBM Research) · Hui Wu (IBM Research) · Song Feng (IBM Research) · Vicente Ordonez (University of Virginia)

Visual Sequence Learning in Hierarchical Prediction Networks and Primate Visual Cortex
JIELIN QIU (Shanghai Jiao Tong University) · Ge Huang (Carnegie Mellon University) · Tai Sing Lee (Carnegie Mellon University)

Dual Variational Generation for Low Shot Heterogeneous Face Recognition
Chaoyou Fu (Institute of Automation, Chinese Academy of Sciences) · Xiang Wu (Institue of Automation, Chinese Academy of Science) · Yibo Hu (Institute of Automation, Chinese Academy of Sciences) · Huaibo Huang (Institute of Automation, Chinese Academy of Science) · Ran He (NLPR, CASIA)

Discovering Neural Wirings
Mitchell N Wortsman (University of Washington, Allen Institute for Artificial Intelligence) · Ali Farhadi (University of Washington, Allen Institute for Artificial Intelligence) · Mohammad Rastegari (Allen Institute for Artificial Intelligence (AI2))

On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems
Baekjin Kim (University of Michigan) · Ambuj Tewari (University of Michigan)

Knowledge Extraction with No Observable Data
Jaemin Yoo (Seoul National University) · Minyong Cho (Seoul National University) · Taebum Kim (Seoul National University) · U Kang (Seoul National University)

PAC-Bayes under potentially heavy tails
Matthew Holland (Osaka University)

One-Shot Object Detection with Co-Attention and Co-Excitation
Ting-I Hsieh (National Tsing Hua University) · Yi-Chen Lo (National Tsing Hua University) · Hwann-Tzong Chen (National Tsing Hua University) · Tyng-Luh Liu (Academia Sinica)

Quaternion Knowledge Graph Embeddings
SHUAI ZHANG (University of New South Wales) · Yi Tay (Nanyang Technological University) · Lina Yao (UNSW) · Qi Liu (Facebook AI Research)

Glyce: Glyph-vectors for Chinese Character Representations
Yuxian Meng (Shannon.AI) · Wei Wu (Shannon.AI) · Fei Wang (Shannon.AI) · Xiaoya Li (Shannon.AI) · Ping Nie (Shannon.AI) · Fan Yin (Shannon.AI) · Muyu Li (Shannon.AI) · Qinghong Han (Shannon.AI) · Xiaofei Sun (Shannon.AI) · Jiwei Li (Shannon.AI)

Turbo Autoencoder: Deep learning based channel code for point-to-point communication channels
Yihan Jiang (University of Washington Seattle) · Hyeji Kim (Samsung AI Center Cambridge) · Himanshu Asnani (University of Washington, Seattle) · Sreeram Kannan (University of Washington) · Sewoong Oh (University of Washington) · Pramod Viswanath (UIUC)

Heterogeneous Graph Learning for Visual Commonsense Reasoning
Weijiang Yu (Sun Yat-sen University) · Jingwen Zhou (Sun Yat-sen University) · Weihao Yu (Sun Yat-sen University) · Xiaodan Liang (Sun Yat-sen University) · Nong Xiao (Sun Yat-sen University)

Probabilistic Watershed: Sampling all spanning forests for seeded segmentation and semi-supervised learning
Enrique Fita Sanmartin (Heidelberg University) · Sebastian Damrich (Heidelberg University) · Fred Hamprecht (Heidelberg University)

Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components
Sascha Saralajew (Dr. Ing. h.c. Porsche AG) · Lars G Holdijk (Radboud University Nijmegen) · Maike Rees (Dr. Ing. h.c. F. Porsche AG) · Ebubekir Asan (Dr. Ing. h.c. F. Porsche AG) · Thomas Villmann (Hochschule Mittweida)

Identifying Causal Effects via Context-specific Independence Relations
Santtu Tikka (University of Jyväskylä) · Antti Hyttinen (University of Helsinki) · Juha Karvanen (University of Jyvaskyla)

Bridging Machine Learning and Logical Reasoning by Abductive Learning
Wang-Zhou Dai (Imperial College London) · Qiuling Xu (Purdue University) · Yang Yu (Nanjing University) · Zhi-Hua Zhou (Nanjing University)

Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function
Zihan Zhang (Tsinghua University) · Xiangyang Ji (Tsinghua University)

On the Global Convergence of (Fast) Incremental Expectation Maximization Methods
Belhal Karimi (Ecole Polytechnique) · Hoi-To Wai (Chinese University of Hong Kong) · Eric Moulines (Ecole Polytechnique) · Marc Lavielle (Inria & Ecole Polytechnique)

A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization
Sulaiman Alghunaim (UCLA) · Kun Yuan (UCLA) · Ali H. Sayed (Ecole Polytechnique Fédérale de Lausanne)

Regularizing Trajectory Optimization with Denoising Autoencoders
Rinu Boney (Aalto University) · Norman Di Palo (Sapienza University of Rome) · Mathias Berglund (Curious AI) · Alexander Ilin (Aalto University) · Juho Kannala (Aalto University) · Antti Rasmus (The Curious AI Company) · Harri Valpola (Curious AI)

Learning Hierarchical Priors in VAEs
Alexej Klushyn (Volkswagen Group) · Nutan Chen (Volkswagen Group) · Richard Kurle (Volkswagen Group) · Botond Cseke (Volkswagen Group) · Patrick van der Smagt (Volkswagen Group)

Epsilon-Best-Arm Identification in Pay-Per-Reward Multi-Armed Bandits
Sivan Sabato (Ben-Gurion University of the Negev)

Safe Exploration for Interactive Machine Learning
Matteo Turchetta (ETH Zurich) · Felix Berkenkamp (ETH Zurich) · Andreas Krause (ETH Zurich)

Addressing Failure Detection by Learning Model Confidence
Charles Corbiere (Valeo.ai) · Nicolas THOME (Cnam) · Avner Bar-Hen (CNAM, Paris) · Matthieu Cord (Sorbonne University) · Patrick Pérez (Valeo.ai)

Combinatorial Bayesian Optimization using the Graph Cartesian Product
Changyong Oh (University of Amsterdam) · Jakub Tomczak (Qualcomm AI Research) · Efstratios Gavves (University of Amsterdam) · Max Welling (University of Amsterdam / Qualcomm AI Research)

Fooling Neural Network Interpretations via Adversarial Model Manipulation
Juyeon Heo (Sungkyunkwan University) · Sunghwan Joo (Sungkyunkwan University) · Taesup Moon (Sungkyunkwan University (SKKU))

On Lazy Training in Differentiable Programming
Lénaïc Chizat (INRIA) · Edouard Oyallon (CentraleSupelec) · Francis Bach (INRIA - Ecole Normale Superieure)

Quality Aware Generative Adversarial Networks
Parimala Kancharla (Indian Institute of Technology, Hyderabad) · Sumohana S Channappayya (Indian Institute of Technology Hyderabad)

Copula-like Variational Inference
Marcel Hirt (University College London) · Petros Dellaportas (University College London, Athens University of Economics and Alan Turing Institute) · Alain Durmus (ENS)

Implicit Regularization for Optimal Sparse Recovery
Tomas Vaskevicius (University of Oxford) · Varun Kanade (University of Oxford) · Patrick Rebeschini (University of Oxford)

Locally Private Gaussian Estimation
Matthew Joseph (University of Pennsylvania) · Janardhan Kulkarni (Microsoft Research) · Jieming Mao (Google Research) · Steven Wu (Microsoft Research)

Multi-mapping Image-to-Image Translation via Learning Disentanglement
Xiaoming Yu (Peking University, Shenzhen Graduate School and Peng Cheng Laboratory) · Yuanqi Chen (SECE, Peking University) · Shan Liu (Tencent) · Thomas Li (Shenzhen Graduate School, Peking University) · Ge Li (SECE, Shenzhen Graduate School, Peking University)

Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs
Yusuke Tanaka (NTT) · Toshiyuki Tanaka (Kyoto University) · Tomoharu Iwata (NTT) · Takeshi Kurashima (NTT Corporation) · Maya Okawa (NTT) · Yasunori Akagi (NTT Service Evolution Laboratories, NTT Corporation) · Hiroyuki Toda (NTT Service Evolution Laboratories, NTT Corporation, Japan)

Structured Decoding for Non-Autoregressive Machine Translation
Zhiqing SUN (Peking University) · Zhuohan Li (UC Berkeley) · Haoqing Wang (Peking University) · Di He (Peking University) · Zi Lin (Peking University) · Zhihong Deng (Peking University)

Learning Temporal Pose Estimation from Sparsely-Labeled Videos
Gedas Bertasius (Facebook Research) · Christoph Feichtenhofer (Facebook AI Research) · Du Tran (Facebook) · Jianbo Shi (University of Pennsylvania) · Lorenzo Torresani (Facebook AI Research)

Greedy InfoMax for Biologically Plausible Self-Supervised Representation Learning
Sindy Löwe (University of Amsterdam) · Peter O'Connor (University of Amsterdam) · Bastiaan Veeling (AMLab - University of Amsterdam)

Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
Hongteng Xu (Duke University) · Dixin Luo (Duke University) · Lawrence Carin (Duke University)

Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
Satoshi Tsutsui (Indiana University) · Yanwei Fu (Fudan University, Shanghai; AItrics Inc. Seoul) · David Crandall (Indiana University)

Real-Time Reinforcement Learning
Simon Ramstedt (University of Montreal) · Chris Pal (Montreal Institute for Learning Algorithms, École Polytechnique, Université de Montréal)

Robust Multi-agent Counterfactual Prediction
Alexander Peysakhovich (Facebook) · Christian Kroer (Columbia University) · Adam Lerer (Facebook AI Research)

Approximate Inference Turns Deep Networks into Gaussian Processes
Mohammad Emtiyaz Khan (RIKEN) · Alexander Immer (EPFL) · Ehsan Abedi (EPFL) · Maciej Jan Korzepa (Technical University of Denmark)

Deep Signatures
Patrick Kidger (University of Oxford) · Patric Bonnier (University of Oxford) · Imanol Perez Arribas (University of Oxford) · Cristopher Salvi (University of Oxford) · Terry Lyons (University of Oxford)

Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits
Yogev Bar-On (Tel-Aviv University) · Yishay Mansour (Tel Aviv University / Google)

Convergent Policy Optimization for Safe Reinforcement Learning
Ming Yu (The University of Chicago, Booth School of Business) · Zhuoran Yang (Princeton University) · Mladen Kolar (University of Chicago) · Zhaoran Wang (Northwestern University)

Augmented Neural ODEs
Emilien Dupont (Oxford University) · Arnaud Doucet (Oxford) · Yee Whye Teh (University of Oxford, DeepMind)

Thompson Sampling for Multinomial Logit Contextual Bandits
Min-hwan Oh (Columbia University) · Garud Iyengar (Columbia)

Backpropagation-Friendly Eigendecomposition
Wei Wang (EPFL) · Zheng Dang (Xi'an Jiaotong University) · Yinlin Hu (EPFL) · Pascal Fua (EPFL, Switzerland) · Mathieu Salzmann (EPFL)

FastSpeech: Fast, Robust and Controllable Text to Speech
Yi Ren (Zhejiang University) · Yangjun Ruan (Zhejiang University) · Xu Tan (Microsoft Research) · Tao Qin (Microsoft Research) · Sheng Zhao (Microsoft) · Zhou Zhao (Zhejiang University) · Tie-Yan Liu (Microsoft Research)

Ultrametric Fitting by Gradient Descent
Giovanni Chierchia (ESIEE Paris) · Benjamin Perret (ESIEE/PARIS)

Distinguishing Distributions When Samples Are Strategically Transformed
Hanrui Zhang (Duke University) · Yu Cheng (Duke University) · Vincent Conitzer (Duke University)

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks
Gauthier Gidel (Mila) · Francis Bach (INRIA - Ecole Normale Superieure) · Simon Lacoste-Julien (Mila, Université de Montréal)

Deep Set Prediction Networks
Yan Zhang (University of Southampton) · Jonathon Hare (University of Southampton) · Adam Prugel-Bennett (apb@ecs.soton.ac.uk)

DppNet: Approximating Determinantal Point Processes with Deep Networks
Zelda Mariet (MIT) · Yaniv Ovadia (Google Inc) · Jasper Snoek (Google Brain)

Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
Sai Zhang (Harvard University) · Qi Zhang (Amazon) · Jieyu Lin (University of Toronto)

Neural Lyapunov Control
Ya-Chien Chang (University of California, San Diego) · Nima Roohi (University of California San Diego) · Sicun Gao (University of California, San Diego)

Fully Dynamic Consistent Facility Location
Vincent Cohen-Addad (CNRS & Sorbonne Université) · Niklas Oskar D Hjuler (University of Copenhagen) · Nikos Parotsidis (University of Rome Tor Vergata) · David Saulpic (Ecole normale supérieure) · Chris Schwiegelshohn (Sapienza, University of Rome)

A Stickier Benchmark for General-Purpose Language Understanding Systems
Alex Wang (New York University) · Yada Pruksachatkun (New York University) · Nikita Nangia (NYU) · Amanpreet Singh (Facebook) · Julian Michael (University of Washington) · Felix Hill (Google Deepmind) · Omer Levy (Facebook) · Samuel Bowman (New York University)

A Flexible Generative Framework for Graph-based Semi-supervised Learning
Jiaqi Ma (University of Michigan) · Weijing Tang (University of Michigan) · Ji Zhu (University of Michigan) · Qiaozhu Mei (University of Michigan)

Self-normalization in Stochastic Neural Networks
Georgios Detorakis (University of California, Irvine) · Sourav Dutta (Univ. Notre Dame) · Abhishek Khanna (Univ. Notre Dame) · Matthew Jerry (Univ. Notre Dame) · Suman Datta (Univ. Notre Dame) · Emre Neftci (Institute for Neural Computation, UCSD)

Optimal Decision Tree with Noisy Outcomes
Su Jia (CMU) · viswanath nagarajan (Univ Michigan, Ann Arbor) · Fatemeh Navidi (University of Michigan) · R Ravi (CMU)

Meta-Curvature
Eunbyung Park (UNC Chapel Hill) · Junier Oliva (UNC-Chapel Hill)

Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning
Nathan Kallus (Cornell University) · Masatoshi Uehara (Harvard University)

KerGM: Kernelized Graph Matching
Zhen Zhang (WASHINGTON UNIVERSITY IN ST.LOUIS) · Yijian Xiang (Washington University in St. Louis) · Lingfei Wu (IBM Research AI) · Bing Xue (Washington University in St. Louis) · Arye Nehorai (WASHINGTON UNIVERSITY IN ST.LOUIS)

Transfusion: Understanding Transfer Learning for Medical Imaging
Maithra Raghu (Cornell University and Google Brain) · Chiyuan Zhang (Google Brain) · Jon Kleinberg (Cornell University) · Samy Bengio (Google Research, Brain Team)

Adversarial training for free!
Ali Shafahi (University of Maryland) · Mahyar Najibi (University of Maryland) · Mohammad Amin Ghiasi (University of Maryland) · Zheng Xu (Google AI) · John P Dickerson (University of Maryland) · Christoph Studer (Cornell University) · Larry Davis (University of Maryland) · Gavin Taylor (US Naval Academy) · Tom Goldstein (University of Maryland)

Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients
Jun Sun (Zhejiang University) · Tianyi Chen (University of Minnesota) · Georgios Giannakis (University of Minnesota) · Zaiyue Yang (Southern University of Science and Technology)

Implicitly learning to reason in first-order logic
Vaishak Belle (University of Edinburgh) · Brendan Juba (Washington University in St. Louis)

Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
Kevin Liang (Duke University) · Guoyin Wang (Duke University) · Yitong Li (Duke University) · Ricardo Henao (Duke University) · Lawrence Carin (Duke University)

PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
Yongkai Wu (University of Arkansas) · Lu Zhang (University of Arkanasa) · Xintao Wu (University of Arkansas) · Hanghang Tong (Arizona State University)

Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration
Jianchun Chen (New York University) · Lingjing Wang (New York University) · Xiang Li (New York University) · Yi Fang (New York University)

Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds
Nathan Kallus (Cornell University) · Angela Zhou (Cornell University)

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the XAUC Metric
Nathan Kallus (Cornell University) · Angela Zhou (Cornell University)

HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models
Sharon Zhou (Stanford University) · Mitchell L Gordon (Stanford University) · Ranjay Krishna (Stanford University) · Austin Narcomey (Stanford University) · Li Fei-Fei (Stanford University) · Michael Bernstein (Stanford University)

First order expansion of convex regularized estimators
Pierre Bellec (rutgers) · Arun Kuchibhotla (Wharton Statistics)

Capacity Bounded Differential Privacy
Kamalika Chaudhuri (UCSD) · Jacob Imola (UCSD) · Ashwin Machanavajjhala (Duke)

Universal Boosting Variational Inference
Trevor Campbell (UBC) · Xinglong Li (The University of British Columbia)

SGD on Neural Networks Learns Functions of Increasing Complexity
Dimitris Kalimeris (Harvard) · Gal Kaplun (Harvard University) · Preetum Nakkiran (Harvard) · Ben Edelman (Harvard University) · Tristan Yang (Harvard University) · Boaz Barak (Harvard University) · Haofeng Zhang (Harvard University)

The Landscape of Non-convex Empirical Risk with Degenerate Population Risk
Shuang Li (Colorado School of Mines) · Gongguo Tang (Colorado School of Mines) · Michael B Wakin (Colorado School of Mines)

Making AI Forget You: Data Deletion in Machine Learning
Tony Ginart (Stanford University) · Melody Guan (Stanford University) · Gregory Valiant (Stanford University) · James Zou (Stanford)

Practical Differentially Private Top-k Selection with Pay-what-you-get Composition
David Durfee (Georgia Tech) · Ryan Rogers (LinkedIn)

Conformalized Quantile Regression
Yaniv Romano (Stanford University) · Evan Patterson (Stanford University) · Emmanuel Candes (Stanford University)

Thompson Sampling with Information Relaxation Penalties
Seungki Min (Columbia Business School) · Costis Maglaras (Columbia Business School) · Ciamac C Moallemi (Columbia University)

Deep Generalized Method of Moments for Instrumental Variable Analysis
Andrew Bennett (Cornell University) · Nathan Kallus (Cornell University) · Tobias Schnabel (Cornell University)

Learning Sample-Specific Models with Low-Rank Personalized Regression
Benjamin Lengerich (Carnegie Mellon University) · Bryon Aragam (University of Chicago) · Eric Xing (Petuum Inc. / Carnegie Mellon University)

Dance to Music
Hsin-Ying Lee (University of California, Merced) · Xiaodong Yang (NVIDIA Research) · Ming-Yu Liu (Nvidia Research) · Ting-Chun Wang (NVIDIA) · Yu-Ding Lu (UC Merced) · Ming-Hsuan Yang (UC Merced / Google) · Jan Kautz (NVIDIA)

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
Hattie Zhou (Uber) · Janice Lan (Uber AI Labs) · Rosanne Liu (Uber AI Labs) · Jason Yosinski (Uber AI Labs)

Implicit Generation and Modeling with Energy Based Models
Yilun Du (MIT) · Igor Mordatch (OpenAI)

Who Learns? Decomposing Learning into Per-Parameter Loss Contribution
Janice Lan (Uber AI Labs) · Rosanne Liu (Uber AI Labs) · Hattie Zhou (Uber) · Jason Yosinski (Uber AI Labs)

Predicting the Politics of an Image Using Webly Supervised Data
Christopher Thomas (University of Pittsburgh) · Adriana Kovashka (University of Pittsburgh)

Adaptive GNN for Image Analysis and Editing
Lingyu Liang (South China University of Technology) · LianWen Jin (South China University of Technology) · Yong Xu (South China University of Technology)

Ultra Fast Medoid Identification via Correlated Sequential Halving
Tavor Z Baharav (Stanford University) · David Tse (Stanford University)

Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD
PHUONG HA NGUYEN (UCONN) · Lam Nguyen (IBM Thomas J. Watson Research Center) · Marten van Dijk (University of Connecticut)

Asymptotics for Sketching in Least Squares Regression
Edgar Dobriban (Stanford University) · Sifan Liu (Tsinghua University)

MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
Xue Bin Peng (UC Berkeley) · Michael Chang (University of California, Berkeley) · Grace Zhang (1998) · Pieter Abbeel (UC Berkeley Covariant) · Sergey Levine (UC Berkeley)

Exact inference in structured prediction
Kevin Bello (Purdue University) · Jean Honorio (Purdue University)

Coda: An End-to-End Neural Program Decompiler
Cheng Fu (University of California, San Diego) · Huili Chen (UCSD) · Haolan Liu (UCSD) · Xinyun Chen (UC Berkeley) · Yuandong Tian (Facebook AI Research) · Farinaz Koushanfar (UCSD) · Jishen Zhao (UCSD)

Bat-G net: Bat-inspired High-Resolution 3D Image Reconstruction using Ultrasonic Echoes
Gunpil Hwang (KAIST) · Seohyeon Kim (KAIST) · Hyeon-Min Bae (KAIST)

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Sharan Vaswani (Mila, Université de Montréal) · Aaron Mishkin (University of British Columbia) · Issam Laradji (University of British Columbia) · Mark Schmidt (University of British Columbia) · Gauthier Gidel (Mila) · Simon Lacoste-Julien (Mila, Université de Montréal)

Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data
Dominik Linzner (TU Darmstadt) · Michael Schmidt (TU Darmstadt) · Heinz Koeppl (Technische Universität Darmstadt)

Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation
Devin Reich (University of Washington Tacoma) · Ariel Todoki (University of Washington Tacoma) · Rafael Dowsley (Bar-Ilan University) · Martine De Cock (University of Washington Tacoma) · anderson nascimento (UW)

Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy
Jonathan Ullman (Northeastern University) · Adam Sealfon (Massachusetts Institute of Technology)

Learning Representations for Time Series Clustering
Qianli Ma (South China University of Technology) · Zheng jiawei (South China University of Technology) · Sen Li (South China University of Technology) · Gary W Cottrell (UCSD)

Variance Reduced Uncertainty Calibration
Ananya Kumar (Stanford University) · Percy Liang (Stanford University) · Tengyu Ma (Stanford)

A Normative Theory for Causal Inference and Bayes Factor Computation in Neural Circuits
Wenhao Zhang (Carnegie Mellon & U. of Pittsburgh) · Si Wu (Peking University) · Brent Doiron (University of Pittsburgh) · Tai Sing Lee (Carnegie Mellon University)

Unsupervised Keypoint Learning for Guiding Class-conditional Video Prediction
Yunji Kim (Yonsei University) · Seonghyeon Nam (Yonsei University) · In Cho (Yonsei University) · Seon Joo Kim (Yonsei University)

Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks
Yiwen Guo (Intel Labs China) · Ziang Yan (Tsinghua University) · Changshui Zhang (Tsinghua University)

Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction
Difan Zou (University of California, Los Angeles) · Pan Xu (University of California, Los Angeles) · Quanquan Gu (UCLA)

Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling
Qitian Wu (Shanghai Jiao Tong University) · Zixuan Zhang (Shanghai Jiao Tong University) · Xiaofeng Gao (Shanghai Jiaotong University) · Junchi Yan (Shanghai Jiao Tong University) · Guihai Chen (Shanghai Jiao Tong University)

Cross-sectional Learning of Extremal Dependence among Financial Assets
Xing Yan (The Chinese University of Hong Kong) · Qi Wu (City University of Hong Kong) · Wen Zhang (JD Finance)

Principal Component Projection and Regression in Nearly Linear Time through Asymmetric SVRG
Yujia Jin (Stanford University) · Aaron Sidford (Stanford)

Compression with Flows via Local Bits-Back Coding
Jonathan Ho (UC Berkeley) · Evan Lohn (University of California, Berkeley) · Pieter Abbeel (UC Berkeley Covariant)

Exact Rate-Distortion in Autoencoders via Echo Noise
Rob Brekelmans (University of Southern Caifornia) · Daniel Moyer (University of Southern California) · Aram Galstyan (USC Information Sciences Inst) · Greg Ver Steeg (University of Southern California)

iSplit LBI: Individualized Partial Ranking with Ties via Split LBI
Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) · Xinwei Sun (MSRA) · Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) · Xiaochun Cao (Chinese Academy of Sciences) · Qingming Huang (University of Chinese Academy of Sciences) · Yuan Yao (Hong Kong Univ. of Science & Technology)

Self-Supervised Active Triangulation for 3D Human Pose Reconstruction
Aleksis Pirinen (Lund University) · Erik Gärtner (Lund University) · Cristian Sminchisescu (LTH)

MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization
Shangyu Chen (Nanyang Technological University, Singapore) · Wenya Wang (Nanyang Technological University) · Sinno Jialin Pan (Nanyang Technological University, Singapore)

Improved Precision and Recall Metric for Assessing Generative Models
Tuomas Kynkäänniemi (NVIDIA; Aalto University) · Tero Karras (NVIDIA) · Samuli Laine (NVIDIA) · Jaakko Lehtinen (NVIDIA & Aalto University) · Timo Aila (NVIDIA Research)

A First-order Algorithmic Framework for Distributionally Robust Logistic Regression
Jiajin Li (The Chinese University of Hong Kong) · Sen Huang (The Chinese University of Hong Kong) · Anthony Man-Cho So (CUHK)

PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
Yikang LI (The Chinese University of Hong Kong) · Tao Ma (Northwestern Polytechnical University) · Yeqi Bai (Nanyang Technological University) · Nan Duan (Microsoft Research) · Sining Wei (Microsoft Research) · Xiaogang Wang (The Chinese University of Hong Kong)

Concomitant Lasso with Repetitions (CLaR): beyond averaging multiple realizations of heteroscedastic noise
Quentin Bertrand (INRIA) · Mathurin Massias (Inria) · Alexandre Gramfort (INRIA, Université Paris-Saclay) · Joseph Salmon (Université de Montpellier)

Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
Han Zhu (Alibaba Group) · Daqing Chang (Alibaba Group) · Ziru Xu (Alibaba Group) · Pengye Zhang (Alibaba Group) · Xiang Li (Alibaba Group) · Jie He (Alibaba Group) · Han Li (Alibaba Group) · Jian Xu (Alibaba Group) · Kun Gai (Alibaba Group)

Learning Generalizable Device Placement Algorithms for Distributed Machine Learning
ravichandra addanki (Massachusetts Institute of Technology) · Shaileshh Bojja Venkatakrishnan (Massachusetts Institute of Technology) · Shreyan Gupta (MIT) · Hongzi Mao (MIT) · Mohammad Alizadeh (Massachusetts Institute of Technology)

Uncoupled Regression from Pairwise Comparison Data
Liyuan Xu (The University of Tokyo / RIKEN) · Junya Honda () · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / University of Tokyo)

Cross Attention Network for Few-shot Classification
Ruibing Hou (Institute of Computing Technology，Chinese Academy) · Hong Chang (Institute of Computing Technology, Chinese Academy of Sciences) · Bingpeng MA (University of Chinese Academy of Sciences) · Shiguang Shan (Chinese Academy of Sciences) · Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution
Qing Qu (New York University) · Xiao Li (The Chinese University of Hong Kong) · Zhihui Zhu (Johns Hopkins University)

SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models
Linfeng Zhang (Tsinghua University ) · Zhanhong Tan (Tsinghua University) · Jiebo Song (Institute for Interdisciplinary Information Core Technology) · Jingwei Chen (Tsinghua University) · Chenglong Bao (Tsinghua university) · Kaisheng Ma (Tsinghua University)

Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs
Lorenzo Dall'Amico (GIPSA lab) · Romain Couillet (CentralSupélec) · Nicolas Tremblay (CNRS)

Teaching Multiple Concepts to a Forgetful Learner
Anette Hunziker (ETH Zurich and University of Zurich) · Yuxin Chen (Caltech) · Oisin Mac Aodha (California Institute of Technology) · Manuel Gomez Rodriguez (Max Planck Institute for Software Systems) · Andreas Krause (ETH Zurich) · Pietro Perona (California Institute of Technology) · Yisong Yue (Caltech) · Adish Singla (MPI-SWS)

Regularized Weighted Low Rank Approximation
Frank Ban (UC Berkeley) · David Woodruff (Carnegie Mellon University) · Richard Zhang (UC Berkeley)

Practical and Consistent Estimation of f-Divergences
Paul Rubenstein (MPI for IS) · Olivier Bousquet (Google Brain (Zurich)) · Josip Djolonga (Google Research, Brain Team) · Carlos Riquelme (Google Brain) · Ilya Tolstikhin (MPI for Intelligent Systems)

Approximation Ratios of Graph Neural Networks for Combinatorial Problems
Ryoma Sato (Kyoto University) · Makoto Yamada (Kyoto University) · Hisashi Kashima (Kyoto University/RIKEN Center for AIP)

Thinning for Accelerating the Learning of Point Processes
Tianbo Li (Nanyang Technological University) · Yiping Ke (Nanyang Technological University)

A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models
Maxim Kuznetsov (Insilico Medicine) · Daniil Polykovskiy (Insilico Medicine) · Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow) · Alexander Zhebrak (Insilico Medicine)

Differentially Private Markov Chain Monte Carlo
Mikko Heikkilä (University of Helsinki) · Joonas Jälkö (Aalto University) · Onur Dikmen (Halmstad University) · Antti Honkela (University of Helsinki)

Full-Gradient Representation for Neural Network Visualization
Suraj Srinivas (Idiap Research Institute & EPFL) · François Fleuret (Idiap Research Institute)

q-means: A quantum algorithm for unsupervised machine learning
Iordanis Kerenidis (Université Paris Diderot) · Jonas Landman (Université Paris Diderot) · Alessandro Luongo (IRIF - Atos quantum lab) · Anupam Prakash (Université Paris Diderot)

Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
Sebastian Tschiatschek (Microsoft Research) · Ahana Ghosh (MPI-SWS) · Luis Haug (ETH Zurich) · Rati Devidze (MPI-SWS) · Adish Singla (MPI-SWS)

Limitations of the empirical Fisher approximation
Frederik Kunstner (EPFL) · Philipp Hennig (University of Tübingen and MPI for Intelligent Systems Tübingen) · Lukas Balles (University of Tuebingen)

Flow-based Image-to-Image Translation with Feature Disentanglement
Ruho Kondo (Toyota Central R&D Labs., Inc.) · Keisuke Kawano (Toyota Central R&D Labs., Inc) · Satoshi Koide (Toyota Central R&D Labs.) · Takuro Kutsuna (Toyota Central R&D Labs. Inc.)

Learning dynamic semi-algebraic proofs
Alhussein Fawzi (DeepMind) · Mateusz Malinowski (DeepMind) · Hamza Fawzi (University of Cambridge) · Omar Fawzi (ENS Lyon)

Shape and Time Distorsion Loss for Training Deep Time Series Forecasting Models
Vincent LE GUEN (Conservatoire National des Arts et Métiers) · Nicolas THOME (Cnam)

Understanding attention in graph neural networks
Boris Knyazev (University of Guelph) · Graham W Taylor (University of Guelph) · Mohamed R. Amer (Robust.AI)

Data Cleansing for Models Trained with SGD
Satoshi Hara (Osaka University) · Atsushi Nitanda (The University of Tokyo / RIKEN) · Takanori Maehara (RIKEN AIP)

Curvilinear Distance Metric Learning
Shuo Chen (Nanjing University of Science and Technology) · Lei Luo (Pitt) · Jian Yang (Nanjing University of Science and Technology) · Chen Gong (Nanjing University of Science and Technology) · Jun Li (MIT) · Heng Huang (University of Pittsburgh)

Semantically-Regularized Logic Graph Embeddings
Xie Yaqi (National University of Singapore) · Ziwei Xu (National University of Singapore) · Kuldeep S Meel (National University of Singapore) · Mohan Kankanhalli (National University of Singapore,) · Harold Soh (National University of Singapore)

Modeling Uncertainty by Learning A Hierarchy of Deep Neural Connections
Raanan Y. Rohekar (Intel AI Lab) · Yaniv Gurwicz (Intel AI Lab) · Shami Nisimov (Intel AI Lab) · Gal Novik (Intel AI Lab)

Efficient Graph Generation with Graph Recurrent Attention Networks
Renjie Liao (University of Toronto) · Yujia Li (DeepMind) · Yang Song (Stanford University) · Shenlong Wang (University of Toronto) · Will Hamilton (McGill) · David Duvenaud (University of Toronto) · Raquel Urtasun (Uber ATG) · Richard Zemel (Vector Institute/University of Toronto)

Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms
Mahesh Chandra Mukkamala (Saarland University) · Peter Ochs (Saarland University)

Learning Deep Bilinear Transformation for Fine-grained Image Representation
Heliang Zheng (University of Science and Technology of China) · Jianlong Fu (Microsoft Research) · Zheng-Jun Zha (University of Science and Technology of China) · Jiebo Luo (U. Rochester)

Practical Deep Learning with Bayesian Principles
Kazuki Osawa (Tokyo Institute of Technology) · Siddharth Swaroop (University of Cambridge) · Mohammad Emtiyaz Khan (RIKEN) · Anirudh Jain (Indian Institute of Technology (ISM), Dhanbad) · Runa Eschenhagen (University of Osnabrueck) · Richard E Turner (University of Cambridge) · Rio Yokota (Tokyo Institute of Technology, AIST- Tokyo Tech Real World Big-Data Computation Open Innovation Laboratory (RWBC- OIL), National Institute of Advanced Industrial Science and Technology (AIST))

Training Language GANs from Scratch
Cyprien de Masson d'Autume (Google DeepMind) · Shakir Mohamed (DeepMind) · Mihaela Rosca (Google DeepMind) · Jack Rae (DeepMind, UCL)

Pseudo-Extended Markov chain Monte Carlo
Christopher Nemeth (Lancaster University) · Fredrik Lindsten (Linköping Universituy) · Maurizio Filippone (EURECOM) · James Hensman (PROWLER.io)

Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate
James Jordon (University of Oxford) · Jinsung Yoon (University of California, Los Angeles) · Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)

Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters
Alberto Maria Metelli (Politecnico di Milano) · Amarildo Likmeta (Politecnico di Milano) · Marcello Restelli (Politecnico di Milano)

On Adversarial Mixup Resynthesis
Christopher Beckham (Ecole Polytechnique de Montreal) · Sina Honari (Mila & University of Montreal) · Alex Lamb (UMontreal (MILA)) · vikas verma (Aalto University) · Farnoosh Ghadiri (École Polytechnique de Montréal) · R Devon Hjelm (Microsoft Research) · Yoshua Bengio (Mila) · Chris Pal (MILA, Polytechnique Montréal, Element AI)

A Geometric Perspective on Optimal Representations for Reinforcement Learning
Marc Bellemare (Google Brain) · Will Dabney (DeepMind) · Robert Dadashi-Tazehozi (Google Brain) · Adrien Ali Taiga (Google) · Pablo Samuel Castro (Google) · Nicolas Le Roux (Google Brain) · Dale Schuurmans (Google Inc.) · Tor Lattimore (DeepMind) · Clare Lyle (University of Oxford)

Learning New Tricks From Old Dogs: Multi-Source Transfer Learning From Pre-Trained Networks
Joshua Lee (Massachusetts Institute of Technology) · Prasanna Sattigeri (IBM Research) · Gregory Wornell (MIT)

Understanding and Improving Layer Normalization
Jingjing Xu (Peking University) · Xu Sun (Peking University) · Zhiyuan Zhang (Peking University) · Guangxiang Zhao (Peking University) · Junyang Lin (Alibaba Group)

Uncertainty-based Continual Learning with Adaptive Regularization
Hongjoon Ahn (SKKU) · Donggyu Lee (Sungkyunkwan university) · Sungmin Cha (Sungkyunkwan University) · Taesup Moon (Sungkyunkwan University (SKKU))

LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning
Yali Du (University of Technology Sydney) · Lei Han (Rutgers University) · Meng Fang (Tencent) · Ji Liu (University of Rochester, Tencent AI lab) · Tianhong Dai (Imperial College London) · Dacheng Tao (University of Sydney)

U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging
Mathias Perslev (University of Copenhagen) · Michael H Jensen (University of Copehagen) · Sune Darkner (University of Copenhagen, Denmark) · Poul Jørgen Jennum (Danish Center for Sleep Medicine, Rigshospitalet) · Christian Igel (University of Copenhagen)

Massively scalable Sinkhorn distances via the Nyström method
Jason Altschuler (MIT) · Francis Bach (INRIA - Ecole Normale Superieure) · Alessandro Rudi (INRIA, Ecole Normale Superieure) · Jonathan Weed (MIT)

Double Quantization for Communication-Efficient Distributed Optimization
Yue Yu (Tsinghua University) · Jiaxiang Wu (Tencent AI Lab) · Longbo Huang (IIIS, Tsinghua Univeristy)

Globally optimal score-based learning of directed acyclic graphs in high-dimensions
Bryon Aragam (University of Chicago) · Arash Amini (UCLA) · Qing Zhou (UCLA)

Multi-relational Poincaré Graph Embeddings
Ivana Balazevic (University of Edinburgh) · Carl Allen (University of Edinburgh) · Timothy Hospedales (University of Edinburgh)

No-Press Diplomacy: Modeling Multi-Agent Gameplay
Philip Paquette (Université de Montréal - MILA) · Yuchen Lu (University of Montreal) · SETON STEVEN BOCCO (MILA - Université de Montréal) · Max Smith (University of Michigan) · Satya O.-G. (MILA) · Jonathan K. Kummerfeld (University of Michigan) · Joelle Pineau (McGill University) · Satinder Singh (University of Michigan) · Aaron Courville (U. Montreal)

State Aggregation Learning from Markov Transition Data
Yaqi Duan (Princeton University) · Tracy Ke (Harvard University) · Mengdi Wang (Princeton University)

Disentangling Influence: Using disentangled representations to audit model predictions
Charles Marx (Haverford College) · Richard Phillips (Haverford College) · Sorelle Friedler (Haverford College) · Carlos Scheidegger (The University of Arizona) · Suresh Venkatasubramanian (University of Utah)

Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
David Janz (University of Cambridge) · Jiri Hron (University of Cambridge) · Przemysław Mazur (Wayve) · Katja Hofmann (Microsoft Research) · José Miguel Hernández-Lobato (University of Cambridge) · Sebastian Tschiatschek (Microsoft Research)

Partially Encrypted Deep Learning using Functional Encryption
Theo Ryffel (École Normale Supérieure) · David Pointcheval (École Normale Supérieure) · Francis Bach (INRIA - Ecole Normale Superieure) · Edouard Dufour-Sans (Carnegie Mellon University) · Romain Gay (UC Berkeley)

Decentralized Cooperative Stochastic Bandits
David Martínez-Rubio (University of Oxford) · Varun Kanade (University of Oxford) · Patrick Rebeschini (University of Oxford)

Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem
Gonzalo Mena (Harvard) · Jonathan Weed (MIT)

Efficient Deep Approximation of GMMs
Shirin Jalali (Nokia Bell Labs) · Carl Nuzman (Nokia Bell Labs) · Iraj Saniee (Nokia Bell Labs)

Learning low-dimensional state embeddings and metastable clusters from time series data
Yifan Sun (Carnegie Mellon University) · Yaqi Duan (Princeton University) · Hao Gong (Princeton University) · Mengdi Wang (Princeton University)

Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations
Xu Wang (Shenzhen University) · Jingming He (Shenzhen University) · Lin Ma (Tencent AI Lab)

Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes
Creighton Heaukulani (No Affiliation) · Mark van der Wilk (PROWLER.io)

Kernel Instrumental Variable Regression
Rahul Singh (MIT) · Maneesh Sahani (Gatsby Unit, UCL) · Arthur Gretton (Gatsby Unit, UCL)

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
Hugo Caselles-Dupré (Flowers Laboaratory (ENSTA ParisTech & INRIA) & Softbank Robotics Europe) · Michael Garcia Ortiz (SoftBank Robotics Europe) · David Filliat (ENSTA)

Fast Efficient Hyperparameter Tuning for Policy Gradient Methods
Supratik Paul (University of Oxford) · Vitaly Kurin (RWTH Aachen University) · Shimon Whiteson (University of Oxford)

Offline Contextual Bayesian Optimization
Ian Char (Carnegie Mellon University) · Youngseog Chung (Carnegie Mellon University) · Willie Neiswanger (Carnegie Mellon University) · Kirthevasan Kandasamy (Carnegie Mellon University) · Oak Nelson (Princeton Plasma Physics Lab) · Mark Boyer (Princeton Plasma Physics Lab) · Egemen Kolemen (Princeton Plasma Physics Lab) · Jeff Schneider (Carnegie Mellon University)

Making the Cut: A Bandit-based Approach to Tiered Interviewing
Candice Schumann (University of Maryland) · Zhi Lang (University of Maryland, College Park) · Jeffrey Foster (Tufts University) · John P Dickerson (University of Maryland)

Unsupervised Scalable Representation Learning for Multivariate Time Series
Jean-Yves Franceschi (Sorbonne Université) · Aymeric Dieuleveut (EPFL) · Martin Jaggi (EPFL)

A state-space model for inferring effective connectivity of latent neural dynamics from simultaneous EEG/fMRI
Tao Tu (Columbia University) · John Paisley (Columbia University) · Stefan Haufe (Charité – Universitätsmedizin Berlin) · Paul Sajda (Columbia University)

End to end learning and optimization on graphs
Bryan Wilder (University of Southern California) · Eric Ewing (University of Southern California) · Bistra Dilkina (University of Southern California) · Milind Tambe (USC)

Game Design for Eliciting Distinguishable Behavior
Fan Yang (Carnegie Mellon University) · Liu Leqi (Carnegie Mellon University) · Yifan Wu (Carnegie Mellon University) · Zachary Lipton (Carnegie Mellon University) · Pradeep Ravikumar (Carnegie Mellon University) · Tom M Mitchell (Carnegie Mellon University) · William Cohen (Google AI)

When does label smoothing help?
Rafael Müller (Google Brain) · Simon Kornblith (Google Brain) · Geoffrey E Hinton (Google & University of Toronto)

Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning
Harsh Gupta (University of Illinois at Urbana-Champaign) · R. Srikant (University of Illinois at Urbana-Champaign) · Lei Ying (ASU)

Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks
Lixin Fan (WeBank AI Lab) · Kam Woh Ng (University of Malaya) · Chee Seng Chan (University of Malaya)

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference
Cole Hurwitz (University of Edinburgh) · Kai Xu (University of Ediburgh) · Akash Srivastava (MIT–IBM Watson AI Lab) · Alessio Buccino (University of Oslo) · Matthias Hennig (University of Edinburgh)

Optimal Sketching for Kronecker Product Regression and Low Rank Approximation
Huaian Diao (Northeast Normal University) · Rajesh Jayaram (Carnegie Mellon University) · Zhao Song (UT-Austin) · Wen Sun (Microsoft Research) · David Woodruff (Carnegie Mellon University)

Distribution-Independent PAC Learning of Halfspaces with Massart Noise
Ilias Diakonikolas (USC) · Themis Gouleakis (MPI) · Christos Tzamos (Microsoft Research)

The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
Basri Ronen (Weizmann Inst.) · David Jacobs (University of Maryland, USA) · Yoni Kasten (Weizmann Institute) · Shira Kritchman (Weizmann Institute)

Online Learning for Auxiliary Task Weighting for Reinforcement Learning
Xingyu Lin (Carnegie Mellon University) · Harjatin Baweja (CMU) · George Kantor (CMU) · David Held (CMU)

Blocking Bandits
Soumya Basu (University of Texas at Austin) · Rajat Sen (University of Texas at Austin) · Sujay Sanghavi (UT-Austin) · Sanjay Shakkottai (University of Texas at Austin)

Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities
Wei Qian (Cornell Univeristy) · Yuqian Zhang (Cornell University) · Yudong Chen (Cornell University)

Prior-Free Dynamic Auctions with Low Regret Buyers
Yuan Deng (Duke University) · Jon Schneider (Google Research) · Balasubramanian Sivan (Google Research)

On Single Source Robustness in Deep Fusion Models
Taewan Kim (University of Texas at Austin) · Joydeep Ghosh (UT Austin)

Policy Evaluation with Latent Confounders via Optimal Balance
Andrew Bennett (Cornell University) · Nathan Kallus (Cornell University)

Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting
Rajat Sen (University of Texas at Austin) · Hsiang-Fu Yu (Amazon) · Inderjit S Dhillon (UT Austin & Amazon)

Adaptive Cross-Modal Few-shot Learning
Chen Xing (Montreal Institute of Learning Algorithms) · Negar Rostamzadeh (Elemenet AI) · Boris Oreshkin (Element AI) · Pedro O. Pinheiro (Element AI)

Spectral Modification of Graphs for Improved Spectral Clustering
Ioannis Koutis (New Jersey Institute of Technology) · Huong Le (NJIT)

Hyperbolic Graph Convolutional Neural Networks
Zhitao Ying (Stanford University) · Ines Chami (Stanford University) · Christopher Ré (Stanford) · Jure Leskovec (Stanford University and Pinterest)

Cost Effective Active Search
Shali Jiang (Washington University in St. Louis) · Roman Garnett (Washington University in St. Louis) · Benjamin Moseley (Carnegie Mellon University)

Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs
Jian QIAN (INRIA Lille - Sequel Team) · Ronan Fruit (Inria Lille) · Matteo Pirotta (Facebook AI Research) · Alessandro Lazaric (Facebook Artificial Intelligence Research)

Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks
Xiao Sun (IBM) · Jungwook Choi (Hanyang University) · Chia-Yu Chen (IBM research) · Naigang Wang (IBM T. J. Watson Research Center) · Swagath Venkataramani (IBM Research) · Vijayalakshmi (Viji) Srinivasan (IBM TJ Watson) · Xiaodong Cui (IBM T. J. Watson Research Center) · Wei Zhang (IBM T.J.Watson Research Center) · Kailash Gopalakrishnan (IBM Research)

A Stratified Approach to Robustness for Randomly Smoothed Classifiers
Guang-He Lee (MIT) · Yang Yuan (MIT) · Shiyu Chang (IBM T.J. Watson Research Center) · Tommi Jaakkola (MIT)

Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees
Ruqi Zhang (Cornell University) · Christopher De Sa (Cornell)

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
Ari Morcos (Facebook AI Research) · Haonan Yu (Facebook AI Research) · Michela Paganini (Facebook) · Yuandong Tian (Facebook AI Research)

Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces
Chuan Guo (Cornell University) · Ali Mousavi (Google Brain) · Xiang Wu (Google) · Daniel Holtmann-Rice (Google Inc) · Satyen Kale (Google) · Sashank Reddi (Google) · Sanjiv Kumar (Google Research)

Fair Algorithms for Clustering
Maryam Negahbani (Dartmouth College) · Deeparnab Chakrabarty (Dartmouth) · Nicolas Flores (Dartmouth College) · Suman Bera (UC Santa Cruz)

Learning Mean-Field Games
Xin Guo (University of California, Berkeley) · Anran Hu (University of Californian, Berkeley (UC Berkeley)) · Renyuan Xu (UC Berkeley) · Junzi Zhang (Stanford University)

SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
Igor Fedorov (Arm Research) · Ryan Adams (Princeton University) · Matthew Mattina (ARM) · Paul Whatmough (Arm Research)

Deep imitation learning for molecular inverse problems
Eric Jonas (University of Chicago)

Visual Concept-Metaconcept Learning
Chi Han (Tsinghua University) · Jiayuan Mao (MIT) · Chuang Gan (MIT-IBM Watson AI Lab) · Josh Tenenbaum (MIT) · Jiajun Wu (MIT)

Adaptive Video-to-Video Synthesis via Network Weight Generation
Ting-Chun Wang (NVIDIA) · Ming-Yu Liu (Nvidia Research) · Andrew Tao (Nvidia Corporation) · Guilin Liu (NVIDIA) · Bryan Catanzaro (NVIDIA) · Jan Kautz (NVIDIA)

Neural Similarity Learning
Weiyang Liu (Georgia Institute of Technology) · Zhen Liu (Georgia Institute of Technology) · James M Rehg (Georgia Tech) · Le Song (Ant Financial & Georgia Institute of Technology)

Ordered Memory
Yikang Shen (Mila, University of Montreal, MSR Montreal) · Shawn Tan (Mila) · SeyedArian Hosseini (Iran University of Science and Technology) · Zhouhan Lin (MILA) · Alessandro Sordoni (Microsoft Research) · Aaron Courville (U. Montreal)

MixMatch: A Holistic Approach to Semi-Supervised Learning
David Berthelot (Google Brain) · Nicholas Carlini (Google) · Ian Goodfellow (Google Brain) · Nicolas Papernot () · Avital Oliver (Google Brain) · Colin A Raffel (Google Brain)

Deep Multivariate Quantiles for Novelty Detection
Jingjing Wang (University of Waterloo) · Sun Sun (University of Waterloo) · Yaoliang Yu (University of Waterloo)

Fast Parallel Algorithms for Statistical Subset Selection Problems
Sharon Qian (Harvard) · Yaron Singer (Harvard University)

PHYRE: A New Benchmark for Physical Reasoning
Anton Bakhtin (Facebook AI Research) · Laurens van der Maaten (Facebook) · Justin Johnson (Facebook AI Research) · Laura Gustafson (Facebook AI Research) · Ross Girshick (FAIR)

How many variables should be entered in a principal component regression equation?
Ji Xu (Columbia University) · Daniel Hsu (Columbia University)

Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
Jicong Fan (Cornell University) · Lijun Ding (Cornell University) · Yudong Chen (Cornell University) · Madeleine Udell (Cornell University)

Mutually Regressive Point Processes
Ifigeneia Apostolopoulou (Carnegie Mellon University) · Scott Linderman (Stanford University) · Kyle Miller (Carnegie Mellon University) · Artur Dubrawski (Carnegie Mellon University)

Data-driven Estimation of Sinusoid Frequencies
Gautier Izacard (Ecole Polytechnique) · Sreyas Mohan (NYU) · Carlos Fernandez-Granda (NYU)

E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving
Ziyu Jiang (Texas A&M University) · Yue Wang (Rice University) · Xiaohan Chen (Texas A&M University) · Pengfei Xu (Rice University) · Yang Zhao (Rice University) · Yingyan Lin (Rice University) · Zhangyang Wang (TAMU)

ANODEV2: A Coupled Neural ODE Framework
Tianjun Zhang (University of California, Berkeley) · Zhewei Yao (UC Berkeley) · Amir Gholami (University of California, Berkeley) · Joseph Gonzalez (UC Berkeley) · Kurt Keutzer (EECS, UC Berkeley) · Michael W Mahoney (UC Berkeley) · George Biros (University of Texas at Austin)

Estimating Entropy of Distributions in Constant Space
Jayadev Acharya (Cornell University) · Sourbh Bhadane (Cornell University) · Piotr Indyk (MIT) · Ziteng Sun (Cornell University)

On the Utility of Learning about Humans for Human-AI Coordination
Micah Carroll (UC Berkeley) · Rohin Shah (UC Berkeley) · Mark Ho (UC Berkeley) · Thomas Griffiths (Princeton University) · Sanjit Seshia (UC Berkeley) · Pieter Abbeel (UC Berkeley Covariant) · Anca Dragan (UC Berkeley)

Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium
Gabriele Farina (Carnegie Mellon University) · Chun Kai Ling (Carnegie Mellon University) · Fei Fang (Carnegie Mellon University) · Tuomas Sandholm (Carnegie Mellon University)

Learning in Generalized Linear Contextual Bandits with Stochastic Delays
Zhengyuan Zhou (Stanford University) · Renyuan Xu (UC Berkeley) · Jose Blanchet (Stanford University)

Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
Saeed Mahloujifar (University of Virginia) · Xiao Zhang (University of Virginia) · Mohammad Mahmoody (University of Virginia) · David Evans (University of Virginia)

Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions
Gabriele Farina (Carnegie Mellon University) · Christian Kroer (Columbia University) · Tuomas Sandholm (Carnegie Mellon University)

On Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model
Erik Nijkamp (UCLA) · Mitch Hill (UCLA Department of Statistics) · Song-Chun Zhu (UCLA) · Ying Nian Wu (University of California, Los Angeles)

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Shiyang Li (UCSB) · Xiaoyong Jin (UCSB) · Yao Xuan (UCSB) · Xiyou Zhou (UCSB) · Wenhu Chen (University of California, Santa Barbara) · Yu-Xiang Wang (UC Santa Barbara) · Xifeng Yan (UCSB)

On the Accuracy of Influence Functions for Measuring Group Effects
Pang Wei W Koh (Stanford University) · Kai-Siang Ang (Stanford University) · Hubert Teo (Stanford University) · Percy Liang (Stanford University)

Face Reconstruction from Voice using Generative Adversarial Networks
Yandong Wen (Carnegie Mellon University) · Bhiksha Raj (Carnegie Mellon University) · Rita Singh (Carnegie Mellon University)

Incremental Few-Shot Learning with Attention Attractor Networks
Mengye Ren (University of Toronto / Uber ATG) · Renjie Liao (University of Toronto) · Ethan Fetaya (University of Toronto) · Richard Zemel (Vector Institute/University of Toronto)

On Testing for Biases in Peer Review
Ivan Stelmakh (Carnegie Mellon University) · Nihar Shah (CMU) · Aarti Singh (CMU)

Learning Disentangled Representation for Robust Person Re-identification
Chanho Eom (Yonsei University) · Bumsub Ham (Yonsei University)

Balancing Efficiency and Fairness in On-Demand Ridesourcing
Nixie Lesmana (Nanyang Technological University) · Xuan Zhang (Shanghai Jiaotong University) · Xiaohui Bei (Nanyang Technological University)

Latent Ordinary Differential Equations for Irregularly-Sampled Time Series
Yulia Rubanova (University of Toronto) · Tian Qi Chen (U of Toronto) · David Duvenaud (University of Toronto)

Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion
Yiqi Zhong (University of Southern California) · Cho-Ying Wu (Univ. of Southern California) · Suya You (US Army Research Laboratory) · Ulrich Neumann (USC)

Input Similarity from the Neural Network Perspective
Guillaume Charpiat (INRIA) · Nicolas Girard (Inria Sophia-Antipolis) · Loris Felardos (INRIA) · Yuliya Tarabalka (Inria Sophia-Antipolis)

Adaptive Sequence Submodularity
Marko Mitrovic (Yale University) · Ehsan Kazemi (Yale) · Moran Feldman (Open University of Israel) · Andreas Krause (ETH Zurich) · Amin Karbasi (Yale)

Weight Agnostic Neural Networks
Adam Gaier (Bonn-Rhein-Sieg University of Applied Sciences) · David Ha (Google Brain)

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction
Daniel Freeman (Google Brain) · David Ha (Google Brain) · Luke Metz (Google Brain)

Reducing the variance in online optimization by transporting past gradients
Sébastien Arnold (USC) · Pierre-Antoine Manzagol (Google) · Reza Harikandeh (UBC) · Ioannis Mitliagkas (Mila & University of Montreal) · Nicolas Le Roux (Google Brain)

Characterizing Bias in Classifiers using Generative Models
Daniel McDuff (Microsoft Research) · Shuang Ma (SUNY Buffalo) · Yale Song (Microsoft) · Ashish Kapoor (Microsoft Research)

Optimal Stochastic and Online Learning with Individual Iterates
Yunwen Lei (Southern University of Science and Technology) · Peng Yang (Southern University of Science and Technology) · Ke Tang (Southern University of Science and Technology) · Ding-Xuan Zhou (City University of Hong Kong)

Policy Learning for Fairness in Ranking
Ashudeep Singh (Cornell University) · Thorsten Joachims (Cornell)

Off-Policy Evaluation of Generalization for Deep Q-Learning in Binary Reward Tasks
Alexander Irpan (Google Brain) · Kanishka Rao (Google) · Konstantinos Bousmalis (DeepMind) · Chris Harris (Google) · Julian Ibarz (Google Inc.) · Sergey Levine (Google)

Regularized Gradient Boosting
Corinna Cortes (Google Research) · Mehryar Mohri (Courant Inst. of Math. Sciences & Google Research) · Dmitry Storcheus (Google Research)

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
Atilim Gunes Baydin (University of Oxford) · Lei Shao (Intel Corporation) · Wahid Bhimji (Berkeley lab) · Lukas Heinrich (New York University) · Saeid Naderiparizi (University of British Columbia) · Andreas Munk (University of British Columbia) · Jialin Liu (Lawrence Berkeley National Lab) · Bradley J Gram-Hansen (University of Oxford) · Gilles Louppe (University of Liège) · Lawrence Meadows (Intel Corporation) · Philip Torr (University of Oxford) · Victor Lee (Intel Corporation) · Kyle Cranmer (New York University) · Mr. Prabhat (LBL/NERSC) · Frank Wood (University of British Columbia)

Markov Random Fields for Collaborative Filtering
Harald Steck (Netflix)

A Step Toward Quantifying Independently Reproducible Machine Learning Research
Edward Raff (Booz Allen Hamilton)

Scalable Global Optimization via Local Bayesian Optimization
David Eriksson (Uber AI) · Matthias Poloczek (University of Arizona) · Jacob Gardner (Uber AI Labs) · Ryan Turner (Uber AI Labs) · Michael Pearce (Warwick University)

Time-series Generative Adversarial Networks
Jinsung Yoon (University of California, Los Angeles) · Daniel Jarrett (University of Cambridge) · M Van Der Schaar (University of California, Los Angeles)

On Accelerating Training of Transformer-Based Language Models
Qian Yang (Duke University) · Zhouyuan Huo (University of Pittsburgh) · Wenlin Wang (Duke Univeristy) · Lawrence Carin (Duke University)

A Refined Margin Distribution Analysis for Forest Representation Learning
Shen-Huan Lyu (Nanjing University) · Liang Yang (Nanjing University) · Zhi-Hua Zhou (Nanjing University)

Robustness to Adversarial Perturbations in Learning from Incomplete Data
Amir Najafi (Sharif University of Technology) · Shin-ichi Maeda (Preferred Networks) · Masanori Koyama (Preferred Networks Inc. ) · Takeru Miyato (Preferred Networks, Inc.)

Exploring Unexplored Tensor Decompositions for Convolutional Neural Networks
Kohei Hayashi (Preferred Networks) · Taiki Yamaguchi (The University of Tokyo) · Yohei Sugawara (Preferred Networks, Inc.) · Shin-ichi Maeda (Preferred Networks)

An Adaptive Empirical Bayesian Method for Sparse Deep Learning
Wei Deng (Purdue University) · Xiao Zhang (Purdue University) · Faming Liang (Purdue University) · Guang Lin (Purdue University)

Adaptive Influence Maximization with Myopic Feedback
Binghui Peng (Tsinghua University) · Wei Chen (Microsoft Research)

Focused Quantization for Sparse CNNs
Yiren Zhao (University of Cambridge) · Xitong Gao (Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences) · Daniel Bates (University of Cambridge) · Robert Mullins (University of Cambridge) · Cheng-Zhong Xu (University of Macau)

Quantum Embedding of Knowledge for Reasoning
Dinesh Garg (IBM Research - India) · Shajith Ikbal Mohamed (IBM Research AI, India) · Santosh Srivastava (IBM Research AI) · Harit Vishwakarma (IBM Research AI) · Hima Karanam (IBM Research AI) · L Venkat Subramaniam (IBM India Research Lab)

Optimal Best Markovian Arm Identification with Fixed Confidence
Vrettos Moulos (UC Berkeley)

Limiting Extrapolation in Linear Approximate Value Iteration
Andrea Zanette (Stanford University) · Alessandro Lazaric (Facebook Artificial Intelligence Research) · Mykel J Kochenderfer (Stanford University) · Emma Brunskill (Stanford University)

Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model
Andrea Zanette (Stanford University) · Mykel J Kochenderfer (Stanford University) · Emma Brunskill (Stanford University)

Invertible Convolutional Flow
Mahdi Karami (University of Alberta) · Dale Schuurmans (Google) · Jascha Sohl-Dickstein (Google Brain) · Laurent Dinh (Google Research) · Daniel Duckworth (Google Brain)

A Latent Variational Framework for Stochastic Optimization
Philippe Casgrain (University of Toronto)

Topology-Preserving Deep Image Segmentation
Xiaoling Hu (Stony Brook University) · Fuxin Li (Oregon State University) · Dimitris Samaras (Stony Brook University) · Chao Chen (Stony Brook University)

Connective Cognition Network for Directional Visual Commonsense Reasoning
Aming Wu (Tianjin University) · Linchao Zhu (University of Sydney, Technology) · Yahong Han (Tianjin University) · Yi Yang (UTS)

Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms
Vikas Garg (MIT) · Tamar Pichkhadze (MIT)

A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning
Francisco Garcia (University of Massachusetts - Amherst) · Philip Thomas (University of Massachusetts Amherst)

Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently
Xiao Liu (Peking University) · Xiaolong Zou (Peking University) · Zilong Ji (Beijing Normal University) · Gengshuo Tian (Beijing Normal University) · Yuanyuan Mi (Weizmann Institute of Science) · Tiejun Huang (Peking University) · K. Y. Michael Wong (Department of Physics, Hong Kong University of Science and Technology) · Si Wu (Peking University)

Learning Disentangled Representations for Recommendation
Jianxin Ma (Tsinghua University) · Chang Zhou (Alibaba Group) · Peng Cui (Tsinghua University) · Hongxia Yang (Alibaba Group) · Wenwu Zhu (Tsinghua University)

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
Simon Du (Carnegie Mellon University) · Kangcheng Hou (Zhejiang University) · Ruslan Salakhutdinov (Carnegie Mellon University) · Barnabas Poczos (Carnegie Mellon University) · Ruosong Wang (Carnegie Mellon University) · Keyulu Xu (MIT)

In-Place Near Zero-Cost Memory Protection for DNN
Hui Guan (North Carolina State University) · Lin Ning (NCSU) · Zhen Lin (NCSU) · Xipeng Shen (North Carolina State University) · Huiyang Zhou (NCSU) · Seung-Hwan Lim (Oak Ridge National Laboratory)

Acceleration via Symplectic Discretization of High-Resolution Differential Equations
Bin Shi (UC Berkeley) · Simon Du (Carnegie Mellon University) · Weijie Su (University of Pennsylvania) · Michael Jordan (UC Berkeley)

XLNet: Generalized Autoregressive Pretraining for Language Understanding
Zhilin Yang (Tsinghua University) · Zihang Dai (Carnegie Mellon University) · Yiming Yang (CMU) · Jaime Carbonell (CMU) · Ruslan Salakhutdinov (Carnegie Mellon University) · Quoc V Le (Google)

Comparison Against Task Driven Artificial Neural Networks Reveals Functional Properties in Mouse Visual Cortex
Jianghong Shi (University of Washington) · Eric Shea-Brown (University of Washington) · Michael Buice (Allen Institute for Brain Science)

Mixtape: Breaking the Softmax Bottleneck Efficiently
Zhilin Yang (Tsinghua University) · Thang Luong (Google) · Ruslan Salakhutdinov (Carnegie Mellon University) · Quoc V Le (Google)

Variance Reduced Policy Evaluation with Smooth Function Approximation
Hoi-To Wai (Chinese University of Hong Kong) · Mingyi Hong (University of Minnesota) · Zhuoran Yang (Princeton University) · Zhaoran Wang (Northwestern University) · Kexin Tang (University of Minnesota)

Learning GANs and Ensembles Using Discrepancy
Ben Adlam (Google) · Corinna Cortes (Google Research) · Mehryar Mohri (Courant Inst. of Math. Sciences & Google Research) · Ningshan Zhang (NYU)

Co-Generation with GANs using AIS based HMC
Tiantian Fang (University of Illinois Urbana-Champaign) · Alexander Schwing (University of Illinois at Urbana-Champaign)

AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification
Ronghui You (Fudan University) · Zihan Zhang (Fudan University) · Ziye Wang (Fudan University) · Suyang Dai (Fudan University) · Hiroshi Mamitsuka (Kyoto University) · Shanfeng Zhu (Fudan University)

Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs
Himanshu Sahni (Georgia Institute of Technology) · Toby Buckley (Offworld Inc.) · Pieter Abbeel (University of California, Berkley & OpenAI) · Ilya Kuzovkin (Offworld Inc.)

Abstract Reasoning with Distracting Features
Kecheng Zheng (University of Science and Technology of China) · Zheng-Jun Zha (University of Science and Technology of China) · Wei Wei (Google AI)

Generalized Block-Diagonal Structure Pursuit: Learning Soft Latent Task Assignment against Negative Transfer
Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) · Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) · Yangbangyan Jiang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) · Xiaochun Cao (Chinese Academy of Sciences) · Qingming Huang (University of Chinese Academy of Sciences)

Adversarial Training and Robustness for Multiple Perturbations
Florian Tramer (Stanford University) · Dan Boneh (Stanford University)

Doubly-Robust Lasso Bandit
Gi-Soo Kim (Seoul National University) · Myunghee Cho Paik (Seoul National University)

DM2C: Deep Mixed-Modal Clustering
Yangbangyan Jiang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) · Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) · Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of Chinese Academy of Sciences) · Xiaochun Cao (Chinese Academy of Sciences) · Qingming Huang (University of Chinese Academy of Sciences)

MaCow: Masked Convolutional Generative Flow
Xuezhe Ma (Carnegie Mellon University) · Xiang Kong (Carnegie Mellon University) · Shanghang Zhang (Carnegie Mellon University) · Eduard Hovy (Carnegie Mellon University)

Learning by Abstraction: The Neural State Machine for Visual Reasoning
Drew Hudson (Stanford) · Christopher Manning (Stanford University)

Adaptive Gradient-Based Meta-Learning Methods
Mikhail Khodak (CMU) · Maria-Florina Balcan (Carnegie Mellon University) · Ameet Talwalkar (CMU)

Equipping Experts/Bandits with Long-term Memory
Kai Zheng (Peking University) · Haipeng Luo (University of Southern California) · Ilias Diakonikolas (USC) · Liwei Wang (Peking University)

A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning
Wenhao Yang (Peking University) · Xiang Li (Peking University) · Zhihua Zhang (Peking University)

Scalable inference of topic evolution via models for latent geometric structures
Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab) · Zhiwei Fan (University of Wisconsin-Madison) · Aritra Guha (University of Michigan) · Paraschos Koutris (University of Wisconsin-Madison) · XuanLong Nguyen (University of Michigan)

Effective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network
Siqi Wang (National University of Defense Technology) · Yijie Zeng (Nanyang Technological University) · Xinwang Liu (National University of Defense Technology) · En Zhu (National University of Defense Technology) · Jianping Yin (Dongguan University of Technology) · Chuanfu Xu (National University of Defense Technology) · Marius Kloft (TU Kaiserslautern)

Deep Active Learning with a Neural Architecture Search
Yonatan Geifman (Technion) · Ran El-Yaniv (Technion)

Efficiently escaping saddle points on manifolds
Christopher Criscitiello (Princeton University) · Nicolas Boumal (Princeton University)

AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
Jiong Zhang (University of Texas at Austin) · Hsiang-Fu Yu (Amazon) · Inderjit S Dhillon (UT Austin & Amazon)

DFNets: Spectral CNNs for Graphs with Feedback-looped Filters
W. O. K. Asiri Suranga Wijesinghe (The Australian National University) · Qing Wang (Australian National University)

Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning
Wonjae Kim (Kakao Corporation) · Yoonho Lee (Kakao Corporation)

Comparing Unsupervised Word Translation Methods Step by Step
Mareike Hartmann (University of Copenhagen) · Yova Kementchedjhieva (University of Copenhagen) · Anders Søgaard (University of Copenhagen)

Learning from Crap Data via Generation
Tianyu Guo (Peking University) · Chang Xu (University of Sydney) · Boxin Shi (Peking University) · Chao Xu (Peking University) · Dacheng Tao (University of Sydney)

Constrained deep neural network architecture search for IoT devices accounting hardware calibration
Florian Scheidegger (IBM Research -- Zurich) · Luca Benini (ETHZ, University of Bologna ) · Costas Bekas (IBM Research GmbH) · A. Cristiano I. Malossi (IBM Research - Zurich)

Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection
Yihe Dong (Microsoft Research) · Sam Hopkins (UC Berkeley) · Jerry Li (Microsoft)

Iterative Least Trimmed Squares for Mixed Linear Regression
Yanyao Shen (UT Austin) · Sujay Sanghavi (UT-Austin)

Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces
Yu Qi (Zhejiang University) · Bin Liu (Nanjing University of Posts and Telecommunications) · Yueming Wang (Zhejiang University) · Gang Pan (Zhejiang University)

Divergence-Augmented Policy Optimization
Qing Wang (Tencent AI Lab) · Yingru Li (The Chinese University of Hong Kong, Shenzhen) · Jiechao Xiong (Tencent AI Lab) · Tong Zhang (Tencent AI Lab)

Intrinsic dimension of data representations in deep neural networks
Alessio Ansuini (International School for Advanced Studies (SISSA)) · Alessandro Laio (International School for Advanced Studies (SISSA)) · Jakob H Macke (Technical University of Munich, Munich, Germany) · Davide Zoccolan (Visual Neuroscience Lab, International School for Advanced Studies (SISSA))

Towards a Zero-One Law for Column Subset Selection
Zhao Song (University of Washington) · David Woodruff (Carnegie Mellon University) · Peilin Zhong (Columbia University)

Compositional De-Attention Networks
Yi Tay (Nanyang Technological University) · Anh Tuan Luu (MIT CSAIL) · Aston Zhang (Amazon AI) · Shuohang Wang (Singapore Management University) · Siu Cheung Hui (Nanyang Technological University)

Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
Jian Ni (University of Science and Technology of China) · Shanghang Zhang (Carnegie Mellon University) · Haiyong Xie (University of Science and Technology of China)

Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
Zeyuan Allen-Zhu (Microsoft Research) · Yuanzhi Li (Princeton) · Yingyu Liang (University of Wisconsin Madison)

Mining GOLD Samples for Conditional GANs
Sangwoo Mo (KAIST) · Chiheon Kim (Kakao Brain) · Sungwoong Kim (Kakao Brain) · Minsu Cho (POSTECH) · Jinwoo Shin (KAIST; AITRICS)

Deep Model Transferability from Attribution Maps
Jie Song (Zhejiang University) · Yixin Chen (Zhejiang University) · Xinchao Wang (Stevens Institute of Technology) · Chengchao Shen (Zhejiang University) · Mingli Song (Zhejiang University)

Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Derek C Yang (UC San Diego) · Li Zhao (Microsoft Research) · Zichuan Lin (Tsinghua University) · Tao Qin (Microsoft Research) · Jiang Bian (Microsoft) · Tie-Yan Liu (Microsoft Research Asia)

Direct Optimization through argmaxarg⁡max for Discrete Variational Auto-Encoder
Guy Lorberbom (Technion) · Tommi Jaakkola (MIT) · Andreea Gane (Google AI) · Tamir Hazan (Technion)

Distributional Reward Decomposition for Reinforcement Learning
Zichuan Lin (Tsinghua University) · Li Zhao (Microsoft Research) · Derek C Yang (UC San Diego) · Tao Qin (Microsoft Research) · Tie-Yan Liu (Microsoft Research Asia) · Guangwen Yang (Tsinghua University)

L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
Yilun Xu (Peking University) · Peng Cao (Peking University) · Yuqing Kong (Peking University) · Yizhou Wang (Peking University)

Convergence Guarantees for Adaptive Bayesian Quadrature Methods
Motonobu Kanagawa (EURECOM) · Philipp Hennig (University of Tübingen and MPI for Intelligent Systems Tübingen)

Progressive Augmentation of GANs
Dan Zhang (Bosch Center for Artificial Intelligence) · Anna Khoreva (Bosch Center for AI)

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
Ali Kavis (EPFL) · Yehuda Kfir Levy (ETH) · Francis Bach (INRIA - Ecole Normale Superieure) · Volkan Cevher (EPFL)

Meta-Surrogate Benchmarking for Hyperparameter Optimization
Aaron Klein (Amazon Berlin) · Zhenwen Dai (Spotify) · Frank Hutter (University of Freiburg) · Neil Lawrence (Amazon) · Javier Gonzalez (Amazon)

Learning to Perform Local Rewriting for Combinatorial Optimization
Xinyun Chen (UC Berkeley) · Yuandong Tian (Facebook AI Research)

Anti-efficient encoding in emergent communication
Rahma Chaabouni (LSCP-FAIR) · Eugene Kharitonov (Facebook AI) · Emmanuel Dupoux (Ecole des Hautes Etudes en Sciences Sociales) · Marco Baroni (University of Trento)

Singleshot : a scalable Tucker tensor decomposition
Abraham Traore () · Maxime Berar (Université de Rouen) · Alain Rakotomamonjy (Université de Rouen Normandie Criteo AI Lab)

Neural Machine Translation with Soft Prototype
Yiren Wang (University of Illinois at Urbana-Champaign) · Yingce Xia (Microsoft Research Asia) · Fei Tian (Microsoft Research) · Fei Gao (University of Chinese Academy of Sciences) · Tao Qin (Microsoft Research) · Cheng Xiang Zhai (University of Illinois at Urbana-Champaign) · Tie-Yan Liu (Microsoft Research)

Reliable training and estimation of variance networks
Nicki Skafte Detlefsen (Technical University of Denmark) · Martin Jørgensen (Technical University of Denmark) · Søren Hauberg (Technical University of Denmark)

On the Statistical Properties of Multilabel Learning
Weiwei Liu (Wuhan University)

Bayesian Learning of Sum-Product Networks
Martin Trapp (Graz University of Technology) · Robert Peharz (University of Cambridge) · Hong Ge (University of Cambridge) · Franz Pernkopf (Signal Processing and Speech Communication Laboratory, Graz, Austria) · Zoubin Ghahramani (Uber and University of Cambridge)

Bayesian Batch Active Learning as Sparse Subset Approximation
Robert Pinsler (University of Cambridge) · Jonathan Gordon (University of Cambridge) · Eric Nalisnick (University of Cambridge) · José Miguel Hernández-Lobato (University of Cambridge)

Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation
zengfeng Huang (Fudan University) · Ziyue Huang (HKUST) · Yilei WANG (The Hong Kong University of Science and Technology) · Ke Yi (" Hong Kong University of Science and Technology, Hong Kong")

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Xiaohan Ding (Tsinghua University) · guiguang ding (Tsinghua University, China) · Xiangxin Zhou (Tsinghua University) · Yuchen Guo (Tsinghua University) · Jungong Han (Lancaster University) · Ji Liu (University of Rochester, Tencent AI lab)

Variational Bayesian Decision-making for Continuous Utilities
Tomasz Kuśmierczyk (University of Helsinki) · Joseph Sakaya (University of Helsinki) · Arto Klami (University of Helsinki)

The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks
Ryo Karakida (National Institute of Advanced Industrial Science and Technology) · Shotaro Akaho (AIST) · Shun-ichi Amari (RIKEN)

Single-Model Uncertainties for Deep Learning
Natasa Tagasovska (University of Lausanne) · David Lopez-Paz (Facebook AI Research)

Is Deeper Better only when Shallow is Good?
Eran Malach (Hebrew University Jerusalem Israel) · Shai Shalev-Shwartz (Mobileye & HUJI)

Wasserstein Weisfeiler-Lehman Graph Kernels
Matteo Togninalli (ETH Zürich) · Elisabetta Ghisu (ETH Zurich) · Felipe Llinares-Lopez (ETH Zürich) · Bastian Rieck (MLCB, D-BSSE, ETH Zurich) · Karsten Borgwardt (ETH Zurich)

Domain Generalization via Model-Agnostic Learning of Semantic Features
Qi Dou (Imperial College London) · Daniel Coelho de Castro (Imperial College London) · Konstantinos Kamnitsas (Imperial College London) · Ben Glocker (Imperial College London)

Grid Saliency for Context Explanations of Semantic Segmentation
Lukas Hoyer (Bosch Center for Artificial Intelligence) · Mauricio Munoz (Bosch Center for Artificial Intelligence) · Prateek Katiyar (Bosch Center for Artificial Intelligence) · Anna Khoreva (Bosch Center for AI) · Volker Fischer (Robert Bosch GmbH, Bosch Center for Artificial Intelligence)

First-order methods almost always avoid saddle points: The case of Vanishing step-sizes
Ioannis Panageas (SUTD) · Georgios Piliouras (Singapore University of Technology and Design) · Xiao Wang (Singapore University of Technology and Design)

Maximum Mean Discrepancy Gradient Flow
Michael Arbel (UCL) · Anna Korba (UCL) · Adil SALIM (KAUST) · Arthur Gretton (Gatsby Unit, UCL)

Oblivious Sampling Algorithms for Private Data Analysis
Olga Ohrimenko (Microsoft Research) · Sajin Sasy (University of Waterloo)

Semi-supervisedly Co-embedding Attributed Networks
Zai Qiao Meng (University of Glasgow) · Shangsong Liang (Sun Yat-sen University) · Jinyuan Fang (Sun Yat-sen University) · Teng Xiao (Sun Yat-sen University)

From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI
Roman Beliy (weizmann institute) · Guy Gaziv (Weizmann Institute of Science) · Assaf Hoogi (Weizmann Institute) · Francesca Strappini (Weizmann Institute of Science) · Tal Golan (Columbia University) · Michal Irani (The Weizmann Institute of Science)

Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
Natasa Tagasovska (University of Lausanne) · Damien Ackerer (Swissquote) · Thibault Vatter (Columbia University)

Nonstochastic Multiarmed Bandits with Unrestricted Delays
Tobias Sommer Thune (University of Copenhagen) · Nicolò Cesa-Bianchi (Università degli Studi di Milano) · Yevgeny Seldin (University of Copenhagen)

BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
Lars Maaløe (Corti) · Marco Fraccaro (Unumed) · Valentin Liévin (DTU) · Ole Winther (Technical University of Denmark)

Code Generation as Dual Task of Code Summarization
Bolin Wei (Peking University) · Ge Li (Peking University) · Xin Xia (Monash University) · Zhiyi Fu (Key Lab of High Confidence Software Technologies (Peking University), Ministry o) · Zhi Jin (Key Lab of High Confidence Software Technologies (Peking University), Ministry o)

Diffeomorphic Temporal Alignment Networks
Ron Shapira weber (Ben Gurion University) · Matan Eyal (Ben Gurion University) · Nicki Skafte Detlefsen (Technical University of Denmark) · Oren Shriki (Ben-Gurion University of the Negev) · Oren Freifeld (Ben-Gurion University)

Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior
Cheng-Chun Hsu (Academia Sinica) · Kuang-Jui Hsu (Qualcomm) · Chung-Chi Tsai (Qualcomm) · Yen-Yu Lin (National Chiao Tung University) · Yung-Yu Chuang (National Taiwan University)

On the Power and Limitations of Random Features for Understanding Neural Networks
Gilad Yehudai (Weizmann Institute of Science) · Ohad Shamir (Weizmann Institute of Science)

Efficient Pure Exploration in Adaptive Round model
tianyuan jin (University of Science and Technology of China) · Jieming SHI (NATIONAL UNIVERSITY OF SINGAPORE) · Xiaokui Xiao (National University of Singapore) · Enhong Chen (University of Science and Technology of China)

Multi-objects Generation with Amortized Structural Regularization
Taufik Xu (Tsinghua University) · Chongxuan LI (Tsinghua University) · Jun Zhu (Tsinghua University) · Bo Zhang (Tsinghua University)

Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time
Karlis Freivalds (Institute of Mathematics and Computer Science) · Emīls Ozoliņš (Institute of Mathematics and Computer Science) · Agris Šostaks (Institute of Mathematics and Computer Science)

DetNAS: Backbone Search for Object Detection
Yukang Chen (Institute of Automation, Chinese Academy of Sciences) · Tong Yang (Megvii Inc.) · Xiangyu Zhang (Megvii Inc (Face++)) · GAOFENG MENG (Institute of Automation, Chinese Academy of Sciences) · Xinyu Xiao (National Laboratory of Pattern recognition (NLPR), Institute of Automation of Chinese Academy of Sciences (CASIA)) · Jian Sun (Megvii, Face++)

Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
Adil SALIM (KAUST) · Dmitry Koralev (KAUST) · Peter Richtarik (KAUST)

Fast AutoAugment
Sungbin Lim (Kakao Brain) · Ildoo Kim (Kakao Brain) · Taesup Kim (Mila / Kakao Brain) · Chiheon Kim (Kakao Brain) · Sungwoong Kim (Kakao Brain)

On the Convergence Rate of Training Recurrent Neural Networks in the Overparameterized Regime
Zeyuan Allen-Zhu (Microsoft Research) · Yuanzhi Li (Princeton) · Zhao Song (University of Washington)

Interval timing in deep reinforcement learning agents
Ben Deverett (DeepMind) · Ryan Faulkner (Deepmind) · Meire Fortunato (DeepMind) · Gregory Wayne (Google DeepMind) · Joel Leibo (DeepMind)

Graph-based Discriminators: Sample Complexity and Expressiveness
Roi Livni (Tel Aviv University) · Yishay Mansour (Tel Aviv University / Google)

Large Scale Structure of Neural Network Loss Landscapes
Stanislav Fort (Stanford University) · Stanislaw Jastrzebski (New York University)

Learning Nonsymmetric Determinantal Point Processes
Mike Gartrell (Criteo AI Lab) · Victor-Emmanuel Brunel (ENSAE ParisTech) · Elvis Dohmatob (Criteo) · Syrine Krichene (Google)

Hypothesis Set Stability and Generalization
Dylan Foster (MIT) · Spencer Greenberg (Spark Wave) · Satyen Kale (Google) · Haipeng Luo (University of Southern California) · Mehryar Mohri (Courant Inst. of Math. Sciences & Google Research) · Karthik Sridharan (Cornell University)

Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
Bo Yang (University of Oxford) · Jianan Wang (DeepMind) · Ronald Clark (Imperial College London) · Qingyong Hu (University of Oxford) · Sen Wang (Heriot-Watt University) · Andrew Markham (University of Oxford) · Niki Trigoni (University of Oxford)

Precision-Recall Balanced Topic Modelling
Seppo Virtanen (Imperial College London) · Mark Girolami (Imperial College London)

Learning Sparse Distributions using Iterative Hard Thresholding
Yibo Zhang (Illinois) · Rajiv Khanna (University of California at Berkeley) · Anastasios Kyrillidis (Rice University ) · Oluwasanmi Koyejo (UIUC)

Discriminative Topic Modeling with Logistic LDA
Iryna Korshunova (Ghent University) · Hanchen Xiong (Twitter) · Mateusz Fedoryszak (Twitter) · Lucas Theis (Twitter)

Quantum Wasserstein Generative Adversarial Networks
Shouvanik Chakrabarti (University of Maryland) · Huang Yiming (University of Maryland & University of Electronic Science and Technology of China) · Tongyang Li (University of Maryland) · Soheil Feizi (University of Maryland, College Park) · Xiaodi Wu (University of Maryland)

Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion
Joan Serrà (Telefónica Research) · Santiago Pascual (Universitat Politècnica de Catalunya) · Carlos Segura Perales (Telefónica Research)

Hyperparameter Learning via Distributional Transfer
Ho Chung Law (University of Oxford) · Peilin Zhao (Tencent AI Lab) · Lucian Chan (University of Oxford) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) · Dino Sejdinovic (University of Oxford)

Discriminator optimal transport
Akinori Tanaka (RIKEN)

High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes
David Salinas (Amazon) · Michael Bohlke-Schneider (Amazon) · Laurent Callot (Amazon) · Jan Gasthaus (Amazon.com) · Roberto Medico (Amazon AWS)

Are Anchor Points Really Indispensable in Label-Noise Learning?
Xiaobo Xia (Xidian University) · Tongliang Liu (The University of Sydney) · Nannan Wang (Xidian University) · Bo Han (RIKEN) · Chen Gong (Nanjing University of Science and Technology) · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / University of Tokyo)

Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
Fenglin Liu (Peking University) · Yuanxin Liu (Institute of Information Engineering, Chinese Academy of Sciences) · Xuancheng Ren (Peking University) · Xiaodong He (JD AI research) · Kai Lei (peking university) · Xu Sun (Peking University)

Differentiable Sorting using Optimal Transport: The Sinkhorn CDF and Quantile Operator
Marco Cuturi (Google and CREST/ENSAE) · Olivier Teboul (Google Brain) · Jean-Philippe Vert ()

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks
Gaël Letarte (Université Laval) · Pascal Germain (INRIA) · Benjamin Guedj (Inria & University College London) · Francois Laviolette (Université Laval)

Likelihood-Free Overcomplete ICA and ApplicationsIn Causal Discovery
Chenwei DING (The University of Sydney) · Mingming Gong (University of Melbourne) · Kun Zhang (CMU) · Dacheng Tao (University of Sydney)

Interior-point Methods Strike Back: Solving the Wasserstein Barycenter Problem
DongDong Ge (Shanghai University of Finance and Economics) · Haoyue Wang (Fudan University) · Zikai Xiong (Fudan University) · Yinyu Ye (Standord)

Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs
Denis Mazur (Yandex) · Vage Egiazarian (Skoltech) · Stanislav Morozov (Yandex) · Artem Babenko (Yandex)

Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections
Boris Muzellec (ENSAE, Institut Polytechnique de Paris) · Marco Cuturi (Google and CREST/ENSAE)

Efficient Non-Convex Stochastic Compositional Optimization Algorithm via Stochastic Recursive Gradient Descent
Huizhuo Yuan (Peking University) · Xiangru Lian (University of Rochester) · Chris Junchi Li (Tencent AI Lab) · Ji Liu (University of Rochester, Tencent AI lab)

On the convergence of single-call stochastic extra-gradient methods
Yu-Guan Hsieh (École normale supérieure, Paris) · Franck Iutzeler (Univ. Grenoble Alpes) · Jérôme Malick (CNRS and LJK) · Panayotis Mertikopoulos (CNRS (French National Center for Scientific Research))

Infra-slow brain dynamics as a marker for cognitive function and decline
Shagun Ajmera (Indian Institute of Science) · Shreya Rajagopal (Indian Institute of Science) · Razi Rehman (Indian Institute of Science) · Devarajan Sridharan (Indian Institute of Science)

Robust Principle Component Analysis with Adaptive Neighbors
Rui Zhang (Northwestern Polytechincal University) · Hanghang Tong (IBM Research)

High-Quality Self-Supervised Deep Image Denoising
Samuli Laine (NVIDIA) · Tero Karras (NVIDIA) · Jaakko Lehtinen (NVIDIA & Aalto University) · Timo Aila (NVIDIA Research)

Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
Sebastian Goldt (Institut de Physique théorique, Paris) · Madhu Advani (Harvard University) · Andrew Saxe (University of Oxford) · Florent Krzakala (École Normale Supérieure) · Lenka Zdeborová (CEA Saclay)

GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
Yuan Liu (Zhejiang University) · Zehong Shen (Zhejiang University) · Zhixuan Lin (Zhejiang University) · Sida Peng (Zhejiang University) · Hujun Bao (Zhejiang University) · Xiaowei Zhou (Zhejiang Univ., China)

Online Prediction of Switching Graph Labelings with Cluster Specialists
Mark Herbster (University College London) · James Robinson (UCL)

Graph-Based Semi-Supervised Learning with Non-ignorable Non-response
Fan Zhou (Shanghai University of Finance and Economics) · Tengfei Li (UNC Chapel Hill) · Haibo Zhou (University of North Carolina at Chapel Hill) · Hongtu Zhu (UNC Chapel Hill) · Ye Jieping (DiDi Chuxing)

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
Andreas Kirsch (University of Oxford) · Joost van Amersfoort (University of Oxford) · Yarin Gal (University of Oxford)

A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off
Yaniv Blumenfeld (Technion) · Dar Gilboa (Columbia University) · Daniel Soudry (Technion)

Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs
Marek Petrik (University of New Hampshire) · Reazul Hasan Russel (University of New Hampshire)

Cross-lingual Language Model Pretraining
Alexis CONNEAU (Facebook) · Guillaume Lample (Facebook AI Research)

Approximate Bayesian Inference for a Mechanistic Model of Vesicle Release at a Ribbon Synapse
Cornelius Schröder (University of Tübingen) · Ben James (University of Sussex) · Leon Lagnado (University of Sussex) · Philipp Berens (University of Tübingen)

Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input
Maxence Ernoult (Université Paris Sud) · Benjamin Scellier () · Yoshua Bengio (Mila) · Damien Querlioz (Univ Paris-Sud) · Julie Grollier (Unité Mixte CNRS/Thalès)

Universal Invariant and Equivariant Graph Neural Networks
Nicolas Keriven (Ecole Normale Supérieure) · Gabriel Peyré (CNRS and ENS)

The bias of the sample mean in multi-armed bandits can be positive or negative
Jaehyeok Shin (Carnegie Mellon University) · Aaditya Ramdas (Carnegie Mellon University) · Alessandro Rinaldo (CMU)

On the Correctness and Sample Complexity of Inverse Reinforcement Learning
Abi Komanduru (Purdue University) · Jean Honorio (Purdue University)

VIREL: A Variational Inference Framework for Reinforcement Learning
Matthew Fellows (University of Oxford) · Anuj Mahajan (University of Oxford) · Tim G. J. Rudner (University of Oxford) · Shimon Whiteson (University of Oxford)

First Order Motion Model for Image Animation
Aliaksandr Siarohin (University of Trento) · Stephane Lathuillere (University of Trento) · Sergey Tulyakov (Snap Inc) · Elisa Ricci (FBK - Technologies of Vision) · Nicu Sebe (University of Trento)

Tensor Monte Carlo: Particle Methods for the GPU era
Laurence Aitchison (University of Cambridge)

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
Alban Laflaquière (ISIR) · Michael Garcia Ortiz (SoftBank Robotics Europe)

Learning from Label Proportions with Generative Adversarial Networks
Jiabin Liu (University of Chinese Academy of Sciences) · Bo Wang (University of International Business and Economics) · Zhiquan Qi (University of Chinese Academy of Sciences) · YingJie Tian (University of Chinese Academy of Sciences) · Yong Shi (University of Chinese Academy of Sciences)

Efficient and Thrifty Voting by Any Means Necessary
Debmalya Mandal (Columbia University) · Ariel D Procaccia (Carnegie Mellon University) · Nisarg Shah (University of Toronto) · David Woodruff (Carnegie Mellon University)

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
Can Qin (Northeastern University) · Haoxuan You (Columbia University) · Lichen Wang (Northeastern University) · C.-C. Jay Kuo (University of Southern California) · Yun Fu (Northeastern University)

ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
Xiangyi Chen (University of Minnesota) · Sijia Liu (MIT-IBM Watson AI Lab, IBM Research AI) · Kaidi Xu (Northeastern University) · Xingguo Li (Princeton University) · Xue Lin (Northeastern University) · Mingyi Hong (University of Minnesota) · David Cox (MIT-IBM Watson AI Lab)

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning
Erwan Lecarpentier (Université de Toulouse, ONERA The French Aerospace Lab) · Emmanuel Rachelson (ISAE-SUPAERO / University of Toulouse)

Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning
Akihiro Kishimoto (IBM Research) · Beat Buesser (IBM Research) · Bei Chen (IBM Research) · Adi Botea (IBM Research)

Toward a Characterization of Loss Functions for Distribution Learning
Nika Haghtalab (Microsoft) · Cameron Musco (Microsoft Research) · Bo Waggoner (U. Colorado, Boulder)

Coresets for Archetypal Analysis
Sebastian Mair (Leuphana University) · Ulf Brefeld (Leuphana)

Emergence of Object Segmentation in Perturbed Generative Models
Adam Bielski (University of Bern) · Paolo Favaro (Bern University, Switzerland)

Optimal Sparse Decision Trees
Xiyang Hu (Duke University) · Cynthia Rudin (Duke) · Margo Seltzer (University of British Columbia)

Escaping from saddle points on Riemannian manifolds
Yue Sun (University of Washington) · Nicolas Flammarion (UC Berkeley) · Maryam Fazel (University of Washington)

Muti-source Domain Adaptation for Semantic Segmentation
Sicheng Zhao (University of California Berkeley) · Bo Li (Harbin Institute of Technology) · Xiangyu Yue (UC Berkeley) · Yang Gu (Didi chuxing) · Pengfei Xu (Didi Chuxing) · Runbo Hu (DiDi Chuxing) · Hua Chai (Didi Chuxing) · Kurt Keutzer (EECS, UC Berkeley)

Localized Structured Prediction
Carlo Ciliberto (Imperial College London) · Francis Bach (INRIA - Ecole Normale Superieure) · Alessandro Rudi (INRIA, Ecole Normale Superieure)

Nonzero-sum Adversarial Hypothesis Testing Games
Sarath Yasodharan (Indian Institute of Science) · Patrick Loiseau (Inria)

Manifold-regression to predict from MEG/EEG brain signals without source modeling
David Sabbagh (INRIA) · Pierre Ablin (Inria) · Gael Varoquaux (Parietal Team, INRIA) · Alexandre Gramfort (INRIA, Université Paris-Saclay) · Denis A. Engemann (INRIA Saclay)

Modeling Tabular data using Conditional GAN
Lei Xu (MIT) · Maria Skoularidou (University of Cambridge) · Alfredo Cuesta Infante (Universidad Rey Juan Carlos) · Kalyan Veeramachaneni (Massachusetts Institute of Technology)

Normalization Helps Training of Quantized LSTM
Lu Hou (Huawei Technologies Co., Ltd) · Jinhua Zhu (University of Science and Technology of China) · James Kwok (Hong Kong University of Science and Technology) · Fei Gao (University of Chinese Academy of Sciences) · Tao Qin (Microsoft Research) · Tie-Yan Liu (Microsoft Research)

Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration
Clarice Poon (University of Bath) · Jingwei Liang (DAMTP, University of Cambridge)

Deep Scale-spaces: Equivariance Over Scale
Daniel Worrall (University of Amsterdam) · Max Welling (University of Amsterdam / Qualcomm AI Research)

GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series
Edward De Brouwer (KU Leuven) · Jaak Simm (KU Leuven) · Adam Arany (University of Leuven) · Yves Moreau (KU Leuven)

Estimating Convergence of Markov chains with L-Lag Couplings
Niloy Biswas (Harvard University) · Pierre E Jacob (Harvard University)

Learning-Based Low-Rank Approximations
Piotr Indyk (MIT) · Ali Vakilian (Massachusetts Institute of Technology) · Yang Yuan (Cornell University)

Implicit Regularization in Deep Matrix Factorization
Sanjeev Arora (Princeton University) · Nadav Cohen (Tel Aviv University) · Wei Hu (Princeton University) · Yuping Luo (Princeton University)

List-decodable Linear Regression
Sushrut Karmalkar (The University of Texas at Austin) · Adam Klivans (UT Austin) · Pravesh Kothari (Princeton University and Institute for Advanced Study)

Learning elementary structures for 3D shape generation and matching
Theo Deprelle (École des ponts ParisTech) · Thibault Groueix (École des ponts ParisTech) · Matthew Fisher (Adobe Research) · Vladimir Kim (Adobe) · Bryan Russell (Adobe) · Mathieu Aubry (École des ponts ParisTech)

On the Hardness of Robust Classification
Pascale Gourdeau (University of Oxford) · Varun Kanade (University of Oxford) · Marta Kwiatkowska (University of Oxford) · James Worrell (University of Oxford)

Foundations of Comparison-Based Hierarchical Clustering
Debarghya Ghoshdastidar (University of Tübingen) · Michaël Perrot (Max Planck Institute for Intelligent Systems) · Ulrike von Luxburg (University of Tübingen)

What the Vec? Towards Probabilistically Grounded Embeddings
Carl Allen (University of Edinburgh) · Ivana Balazevic (University of Edinburgh) · Timothy Hospedales (University of Edinburgh)

Minimizers of the Empirical Risk and Risk Monotonicity
Marco Loog (Delft University of Technology) · Tom Viering (Delft University of Technology, Netherlands) · Alexander Mey (TU Delft)

Explicit Planning for Efficient Exploration in Reinforcement Learning
Liangpeng Zhang (University of Birmingham) · Xin Yao (University of Birmingham)

Lower Bounds on Adversarial Robustness from Optimal Transport
Arjun Nitin Bhagoji (Princeton University) · Daniel Cullina (Princeton University) · Prateek Mittal (Princeton University)

Neural Spline Flows
Conor Durkan (University of Edinburgh) · Arturs Bekasovs (University of Edinburgh) · Iain Murray (University of Edinburgh) · George Papamakarios (DeepMind)

Phase Transitions and Cyclic Phenomena in Bandits with Switching Constraints
David Simchi-Levi (MIT) · Yunzong Xu (MIT)

Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
Koen Helwegen (Plumerai) · James Widdicombe (Plumerai) · Lukas Geiger (Plumerai) · Zechun Liu (HKUST) · Kwang-Ting Cheng (Hong Kong University of Science and Technology) · Koen Helwegen (Plumerai)

Nonlinear scaling of resource allocation in sensory bottlenecks
Laura R Edmondson (University of Sheffield) · Alejandro Jimenez Rodriguez (University of Sheffield) · Hannes P. Saal (University of Sheffield)

Constrained Reinforcement Learning: A Dual Approach
Santiago Paternain (University of Pennsylvania) · Luiz Chamon (University of Pennsylvania) · Miguel Calvo-Fullana (University of Pennsylvania) · Alejandro Ribeiro (University of Pennsylvania)

Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
Niklas Gebauer (Technische Universität Berlin) · Michael Gastegger (Technische Universität Berlin) · Kristof Schütt (TU Berlin)

An adaptive nearest neighbor rule for classification
Akshay Balsubramani (Stanford) · Sanjoy Dasgupta (UC San Diego) · yoav S Freund (UCSD) · Shay Moran (IAS, Princeton)

Coresets for Clustering with Fairness Constraints
Lingxiao Huang (EPFL) · Shaofeng H.-C. Jiang (Weizmann Institute of Science) · Nisheeth Vishnoi (Yale University)

PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments
Ben Graham (Facebook Research) · David Novotny (Facebook AI Research) · Jeremy Reizenstein (Facebook AI Research)

MAVEN: Multi-Agent Variational Exploration
Anuj Mahajan (University of Oxford) · Tabish Rashid (University of Oxford) · Mikayel Samvelyan (Russian-Armenian University) · Shimon Whiteson (University of Oxford)

Competitive Gradient Descent
Florian Schaefer (Caltech) · Anima Anandkumar (NVIDIA / Caltech)

Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses
Ulysse Marteau-Ferey (INRIA) · Francis Bach (INRIA - Ecole Normale Superieure) · Alessandro Rudi (INRIA, Ecole Normale Superieure)

Continual Unsupervised Representation Learning
Dushyant Rao (DeepMind) · Francesco Visin (DeepMind) · Andrei Rusu (DeepMind) · Razvan Pascanu (Google DeepMind) · Yee Whye Teh (University of Oxford, DeepMind) · Raia Hadsell (DeepMind)

Self-Routing Capsule Networks
Taeyoung Hahn (SNUVL) · Myeongjang Pyeon (Seoul National University) · Gunhee Kim (Seoul National University)

The Parameterized Complexity of Cascading Portfolio Scheduling
Eduard Eiben (University of Bergen) · Robert Ganian (TU Wien) · Iyad Kanj (DePaul University, Chicago) · Stefan Szeider (Vienna University of Technology)

Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards
Zhongtian Dai (Toyota Technological Institute at Chicago) · Matthew R. Walter (TTI-Chicago)

Bipartite expander Hopfield networks as self-decoding high-capacity error correcting codes
Rishidev Chaudhuri (University of California, Davis) · Ila Fiete (University of Texas at Austin)

Sequence Modelling with Unconstrained Generation Order
Dmitriy Emelyanenko (Yandex; National Research University Higher School of Economics) · Elena Voita (Yandex; University of Amsterdam) · Pavel Serdyukov (Yandex)

Probabilistic Logic Neural Networks for Reasoning
Meng Qu (MILA) · Jian Tang (HEC Montreal & MILA)

A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families
Brian Axelrod (Stanford) · Ilias Diakonikolas (USC) · Alistair Stewart (University of Southern California) · Anastasios Sidiropoulos (University of Illinois at Chicago) · Gregory Valiant (Stanford University)

A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening
Gecia Bravo Hermsdorff (Princeton University) · Lee Gunderson (Princeton University)

Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
Xuechen Li (Google) · Yi Wu (University of Toronto & Vector Institute) · Lester Mackey (Microsoft Research) · Murat Erdogdu (University of Toronto)

The Implicit Bias of AdaGrad on Separable Data
Qian Qian (the Ohio State University) · Xiaoyuan Qian (Dalian University of Technology)

On two ways to use determinantal point processes for Monte Carlo integration
Guillaume Gautier (CNRS, INRIA, Univ. Lille) · Rémi Bardenet (University of Lille) · Michal Valko (DeepMind Paris and Inria Lille - Nord Europe)

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Zuxuan Wu (UMD) · Caiming Xiong (Salesforce) · Yu-Gang Jiang (Fudan University) · Larry Davis (University of Maryland)

How degenerate is the parametrization of neural networks with the ReLU activation function?
Dennis Elbrächter (University of Vienna) · Julius Berner (University of Vienna) · Philipp Grohs (University of Vienna)

Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks
Wenrui Zhang (Texas A&M University) · Peng Li (Texas A&M University)

Re-examination of the Role of Latent Variables in Sequence Modeling
Guokun Lai (Carnegie Mellon University) · Zihang Dai (Carnegie Mellon University)

Max-value Entropy Search for Multi-Objective Bayesian Optimization
Syrine Belakaria (Washington State University) · Aryan Deshwal (Washington State University) · Janardhan Rao Doppa (Washington State University)

Stein Variational Gradient Descent With Matrix-Valued Kernels
Dilin Wang (UT Austin) · Ziyang Tang (UT Austin) · Chandrajit Bajaj (The University of Texas at Austin) · Qiang Liu (UT Austin)

Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms
Shahana Ibrahim (Oregon State University) · Xiao Fu (Oregon State University) · Nikolaos Kargas (University of Minnesota) · Kejun Huang (University of Florida)

Detecting Overfitting via Adversarial Examples
Roman Werpachowski (DeepMind) · András György (DeepMind) · Csaba Szepesvari (DeepMind/University of Alberta)

A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
Felix Leibfried (PROWLER.io) · Sergio Pascual-Diaz (PROWLER.io) · Jordi Grau-Moya (PROWLER.io)

SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies
Seyed Kamyar Seyed Ghasemipour (University of Toronto) · Shixiang (Shane) Gu (Google Brain) · Richard Zemel (Vector Institute/University of Toronto)

Towards Understanding the Importance of Shortcut Connections in Residual Networks
Tianyi Liu (Georgia Institute of Technolodgy) · Minshuo Chen (Georgia Tech) · Mo Zhou (Duke University) · Simon Du (Carnegie Mellon University) · Enlu Zhou (Georgia Institute of Technology) · Tuo Zhao (Gatech)

Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains
Elliot Meyerson (Cognizant) · Risto Miikkulainen (The University of Texas at Austin; Cognizant)

Solving Interpretable Kernel Dimensionality Reduction
Chieh T Wu (Northeastern University) · Jared Miller (Northeastern University) · Yale Chang (Northeastern University) · Mario Sznaier (Northeastern University) · Jennifer G Dy (Northeastern University)

Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space
Shuo Yang (UT Austin) · Yanyao Shen (UT Austin) · Sujay Sanghavi (UT-Austin)

A Model to Search for Synthesizable Molecules
John Bradshaw (University of Cambridge/MPI Tuebingen) · Brooks Paige (Alan Turing Institute) · Matt J Kusner (University College London) · Marwin Segler (BenevolentAI) · José Miguel Hernández-Lobato (University of Cambridge)

Post training 4-bit quantization of convolutional networks for rapid-deployment
Ron Banner (Intel - Artificial Intelligence Products Group (AIPG)) · Yury Nahshan (Intel corp.) · Daniel Soudry (Technion)

Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes
James Requeima (University of Cambridge / Invenia Labs) · Jonathan Gordon (University of Cambridge) · John Bronskill (University of Cambridge) · Sebastian Nowozin (Microsoft Research) · Richard Turner (Cambridge)

Differentially Private Anonymized Histograms
Ananda Theertha Suresh (Google)

Dynamic Local Regret for Non-convex Online Forecasting
Sergul Aydore (Stevens Institute of Technology) · Tianhao Zhu (Stevens Institute of Techonlogy) · Dean Foster (Amazon)

Learning Local Search Heuristics for Boolean Satisfiability
Emre Yolcu (Carnegie Mellon University) · Barnabas Poczos (Carnegie Mellon University)

Provably Efficient Q-Learning with Low Switching Cost
Yu Bai (Stanford University) · Tengyang Xie (University of Illinois at Urbana-Champaign) · Nan Jiang (University of Illinois at Urbana-Champaign) · Yu-Xiang Wang (UC Santa Barbara)

Solving graph compression via optimal transport
Vikas Garg (MIT) · Tommi Jaakkola (MIT)

PyTorch: An Imperative Style, High-Performance Deep Learning Library
Benoit Steiner (Facebook AI Research) · Zachary DeVito (Facebook AI Research) · Soumith Chintala (Facebook AI Research) · Sam Gross (Facebook) · Adam Paszke (University of Warsaw) · Francisco Massa (Facebook AI Research) · Adam Lerer (Facebook AI Research) · Gregory Chanan (Facebook) · Zeming Lin (Facebook AI Research) · Edward Yang (Facebook) · Alban Desmaison (Oxford University) · Alykhan Tejani (Twitter, Inc.) · Andreas Kopf (Xamla) · James Bradbury (Google Brain) · Luca Antiga (Orobix) · Martin Raison (Nabla) · Natalia Gimelshein (NVIDIA) · Sasank Chilamkurthy (Qure.ai) · Trevor Killeen (Self Employed) · Lu Fang (Facebook) · Junjie Bai (Facebook)

Stability of Graph Scattering Transforms
Fernando Gama (University of Pennsylvania) · Alejandro Ribeiro (University of Pennsylvania) · Joan Bruna (NYU)

A Debiased MDI Feature Importance Measure for Random Forests
Xiao Li (University of California, Berkeley) · Yu Wang (UC Berkeley) · Sumanta Basu (Cornell University) · Karl Kumbier (University of California, Berkeley) · Bin Yu (UC Berkeley)

Difference Maximization Q-learning: Provably Efficient Q-learning with Function Approximation
Simon Du (Carnegie Mellon University) · Yuping Luo (Princeton University) · Ruosong Wang (Carnegie Mellon University) · Hanrui Zhang (Duke University)

Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models
Shanshan Wu (University of Texas at Austin) · Sujay Sanghavi (UT-Austin) · Alexandros Dimakis (University of Texas, Austin)

Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks
Guodong Zhang (University of Toronto) · James Martens (DeepMind) · Roger Grosse (University of Toronto)

Rapid Convergence of the Unadjusted Langevin Algorithm: Log-Sobolev Suffices
Santosh Vempala (Georgia Tech) · Andre Wibisono ()

Learning Distributions Generated by One-Layer ReLU Networks
Shanshan Wu (University of Texas at Austin) · Alexandros Dimakis (University of Texas, Austin) · Sujay Sanghavi (UT-Austin)

Large-scale optimal transport map estimation using projection pursuit
Cheng Meng (University of Georgia) · Yuan Ke (University of Georgia) · Jingyi Zhang (The University of Georgia) · Mengrui Zhang (University of Georgia) · Wenxuan Zhong () · Ping Ma (University of Georgia)

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning
Nicolas Carion (Facebook AI Research Paris) · Nicolas Usunier (Facebook AI Research) · Gabriel Synnaeve (Facebook) · Alessandro Lazaric (Facebook Artificial Intelligence Research)

On Exact Computation with an Infinitely Wide Neural Net
Sanjeev Arora (Princeton University) · Simon Du (Carnegie Mellon University) · Wei Hu (Princeton University) · zhiyuan li (Princeton University) · Ruslan Salakhutdinov (Carnegie Mellon University) · Ruosong Wang (Carnegie Mellon University)

Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning
Gregory Farquhar (University of Oxford) · Shimon Whiteson (University of Oxford) · Jakob Foerster (University of Oxford)

Chirality Nets for Human Pose Regression
Raymond Yeh (University of Illinois at Urbana–Champaign) · Yuan-Ting Hu (University of Illinois Urbana-Champaign) · Alexander Schwing (University of Illinois at Urbana-Champaign)

Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
Minshuo Chen (Georgia Tech) · Haoming Jiang (Georgia Institute of Technology) · Wenjing Liao (Georgia Tech) · Tuo Zhao (Georgia Tech)

Fast Decomposable Submodular Function Minimization using Constrained Total Variation
Senanayak Sesh Kumar Karri (Imperial College, London) · Francis Bach (INRIA - Ecole Normale Superieure) · Thomas Pock (Graz University of Technology)

Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
Guodong Zhang (University of Toronto) · Lala Li (Google) · Zachary Nado (Google Inc.) · James Martens (DeepMind) · Sushant Sachdeva (University of Toronto) · George Dahl (Google Brain) · Chris Shallue (Google Brain) · Roger Grosse (University of Toronto)

Spherical Text Embedding
Yu Meng (University of Illinois at Urbana-Champaign) · Jiaxin Huang (University of Illinois Urbana-Champaign) · Guangyuan Wang (UIUC) · Chao Zhang (Georgia Institute of Technology) · Honglei Zhuang (Google Research) · Lance Kaplan (U.S. Army Research Laboratory) · Jiawei Han (UIUC)

Möbius Transformation for Fast Inner Product Search on Graph
Zhixin Zhou (Baidu Research) · Shulong Tan (Baidu Research) · Zhaozhuo Xu (Baidu Research) · Ping Li (Baidu Research USA)

Hyperbolic Graph Neural Networks
Qi Liu (National University of Singapore) · Maximilian Nickel (Facebook AI Research) · Douwe Kiela (Facebook AI Research)

Average Individual Fairness: Algorithms, Generalization and Experiments
Saeed Sharifi-Malvajerdi (University of Pennsylvania) · Michael Kearns (University of Pennsylvania) · Aaron Roth (University of Pennsylvania)

Fixing the train-test resolution discrepancy
Hugo Touvron (Facebook AI Research) · Andrea Vedaldi (Facebook AI Research and University of Oxford) · Matthijs Douze (Facebook AI Research) · Herve Jegou (Facebook AI Research)

Modeling Dynamic Functional Connectivity with Latent Factor Gaussian Processes
Lingge Li (UC Irvine) · Dustin Pluta (UC Irvine) · Babak Shahbaba (UCI) · Norbert Fortin (UC Irvine) · Hernando Ombao (KAUST) · Pierre Baldi (UC Irvine)

Manipulating a Learning Defender and Ways to Counteract
Jiarui Gan (University of Oxford) · Qingyu Guo (Nanyang Technological University) · Long Tran-Thanh (University of Southampton) · Bo An (Nanyang Technological University) · Michael Wooldridge (Univ of Oxford)

Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations
Andrew Spielberg (Massachusetts Institute of Technology) · Allan Zhao (Massachusetts Institute of Technology) · Yuanming Hu (Massachusetts Institute of Technology) · Tao Du (MIT) · Wojciech Matusik (MIT) · Daniela Rus (Massachusetts Institute of Technology)

Learning to Infer Implicit Surfaces without 3D Supervision
Shichen Liu (Tsinghua University) · Shunsuke Saito (University of Southern California) · Weikai Chen (USC Institute for Creative Technology) · Hao Li (Pinscreen/University of Southern California/USC ICT)

Fast and Accurate Least-Mean-Squares Solvers
Ibrahim Jubran (The University of Haifa) · Alaa Maalouf (The University of Haifa) · Dan Feldman (University of Haifa)

Certifiable Robustness to Graph Perturbations
Aleksandar Bojchevski (Technical University of Munich) · Stephan Günnemann (Technical University of Munich)

Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay 
Frederic Koehler (MIT)

Paradoxes in Fair Machine Learning
Paul Goelz (Carnegie Mellon University) · Anson Kahng (Carnegie Mellon University) · Ariel D Procaccia (Carnegie Mellon University)

Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
Zhuoran Yang (Princeton University) · Yongxin Chen (Georgia Institute of Technology) · Mingyi Hong (University of Minnesota) · Zhaoran Wang (Northwestern University)

The spiked matrix model with generative priors
Benjamin Aubin (Ipht Saclay) · Bruno Loureiro (IPhT Saclay) · Antoine Maillard (Ecole Normale Supérieure) · Florent Krzakala (ENS Paris & Sorbonnes Université) · Lenka Zdeborová (CEA Saclay)

Gradient Dynamics of Shallow Low-Dimensional ReLU Networks
Francis Williams (New York University) · Matthew Trager (NYU) · Daniele Panozzo (NYU) · Claudio Silva (New York University) · Denis Zorin (New York University) · Joan Bruna (NYU)

Robust and Communication-Efficient Collaborative Learning
Amirhossein Reisizadeh (UC Santa Barbara) · Hossein Taheri (UCSB) · Aryan Mokhtari (UT Austin) · Hamed Hassani (UPenn) · Ramtin Pedarsani (UC Santa Barbara)

Multiclass Learning from Contradictions
Sauptik Dhar (LG Electronics) · Vladimir Cherkassky (University of Minnesota) · Mohak Shah (LG Electronics)

Learning from Trajectories via Subgoal Discovery
Sujoy Paul (UC Riverside) · Jeroen Vanbaar (Mitsubishi Electric Research Laboratories) · Amit Roy-Chowdhury (University of California, Riverside, USA )

Distributed Low-rank Matrix Factorization With Exact Consensus
Zhihui Zhu (Johns Hopkins University) · Qiuwei Li (Colorado School of Mines) · Xinshuo Yang (Colorado School of Mines) · Gongguo Tang (Colorado School of Mines) · Michael B Wakin (Colorado School of Mines)

Online Normalization for Training Neural Networks
Vitaliy Chiley (Cerebras Systems) · Ilya Sharapov (Cerebras Systems) · Atli Kosson (Cerebras Systems) · Urs Koster (Cerebras Systems) · Ryan Reece (Cerebras Systems) · Sofia Samaniego de la Fuente (Cerebras Systems) · Vishal Subbiah (Cerebras Systems) · Michael James (Cerebras)

The Synthesis of XNOR Recurrent Neural Networks with Stochastic Logic
Arash Ardakani (McGill University) · Zhengyun Ji (McGill University) · Amir Ardakani (McGill University) · Warren Gross (McGill University)

An adaptive Mirror-Prox method for variational inequalities with singular operators
Kimon Antonakopoulos (Inria) · Veronica Belmega (ENSEA) · Panayotis Mertikopoulos (CNRS (French National Center for Scientific Research))

N-Gram Graph: A Simple Unsupervised Representation for Molecules
Shengchao Liu (UW-Madison) · Mehmet F Demirel (University of Wisconsin-Madison) · Yingyu Liang (University of Wisconsin Madison)

Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory
Bin Hu (University of Illinois at Urbana-Champaign) · Usman A Syed (University of Illinois Urbana Champaign)

Facility Location Problem in Differential Privacy Model Revisited 
Yunus Esencayi (State University of New York at Buffalo) · Marco Gaboardi (Univeristy at Buffalo) · Shi Li (University at Buffalo) · Di Wang (State University of New York at Buffalo)

Revisiting Auxiliary Latent Variables in Generative Models
John Lawson (New York University) · George Tucker (Google Brain) · Bo Dai (Google Brain) · Rajesh Ranganath (New York University)

Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator
Karl Krauth (UC berkeley) · Stephen Tu (UC Berkeley) · Benjamin Recht (UC Berkeley)

A Universally Optimal Multistage Accelerated Stochastic Gradient Method
Necdet Serhat Aybat (Penn State University) · Alireza Fallah (MIT) · Mert Gurbuzbalaban (Rutgers) · Asuman Ozdaglar (Massachusetts Institute of Technology)

From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
Hidenori Tanaka (Stanford) · Aran Nayebi (Stanford University) · Stephen Baccus (Stanford University) · Surya Ganguli (Stanford)

Large Memory Layers with Product Keys
Guillaume Lample (Facebook AI Research) · Alexandre Sablayrolles (Facebook AI Research) · Marc'Aurelio Ranzato (Facebook AI Research) · Ludovic Denoyer (Facebook - FAIR) · Herve Jegou (Facebook AI Research)

Learning Deterministic Weighted Automata with Queries and Counterexamples
Gail Weiss (Technion) · Yoav Goldberg (Bar Ilan University) · Eran Yahav (Technion)

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
Jaehoon Lee (Google Brain) · Lechao Xiao (Google Brain) · Samuel Schoenholz (Google Brain) · Yasaman Bahri (Google Brain) · Roman Novak (Google Brain) · Jascha Sohl-Dickstein (Google Brain) · Jeffrey Pennington (Google Brain)

Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals
Surbhi Goel (UT Austin) · Sushrut Karmalkar (The University of Texas at Austin) · Adam Klivans (UT Austin)

Visualizing and Measuring the Geometry of BERT
Emily Reif (Google) · Ann Yuan (Google) · Martin Wattenberg (Google) · Fernanda B Viegas (Google) · Andy Coenen (Google) · Adam Pearce (Google) · Been Kim (Google)

Self-Critical Reasoning for Robust Visual Question Answering
Jialin Wu (UT Austin) · Raymond Mooney (University of Texas at Austin)

Learning to Screen
Alon Cohen (Technion and Google Inc.) · Avinatan Hassidim (Google) · Haim Kaplan (TAU, GOOGLE) · Yishay Mansour (Tel Aviv University / Google) · Shay Moran (IAS, Princeton)

A Communication Efficient Stochastic Multi-Block Alternating Direction Method of Multipliers
Hao Yu (Alibaba Group (US) Inc )

A Little Is Enough: Circumventing Defenses For Distributed Learning
Gilad Baruch (Bar Ilan University) · Moran Baruch (Bar Ilan University) · Yoav Goldberg (Bar-Ilan University)

Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural Networks
Gunjan Verma (ARL) · Ananthram Swami (Army Research Laboratory, Adelphi)

A Robust Non-Clairvoyant Dynamic Mechanism for Contextual Auctions
Yuan Deng (Duke University) · Sebastien Lahaie (Google Research) · Vahab Mirrokni (Google Research NYC)

Finite-Sample Analysis for SARSA with Linear Function Approximation
Shaofeng Zou (University at Buffalo, the State University of New York) · Tengyu Xu (The Ohio State University) · Yingbin Liang (The Ohio State University)

Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models
Stefano Sarao Mannelli (Institut de Physique Théorique) · Giulio Biroli (ENS) · Chiara Cammarota (King's College London) · Florent Krzakala (École Normale Supérieure) · Lenka Zdeborová (CEA Saclay)

Graph Structured Prediction Energy Networks
Colin Graber (University of Illinois at Urbana-Champaign) · Alexander Schwing (University of Illinois at Urbana-Champaign)

Private Learning Implies Online Learning: An Efficient Reduction
Alon Gonen (Princeton University) · Elad Hazan (Princeton University) · Shay Moran (IAS, Princeton)

Graph Agreement Models for Semi-Supervised Learning
Otilia Stretcu (Carnegie Mellon University) · Krishnamurthy Viswanathan (Google Research) · Dana Movshovitz-Attias (Google) · Emmanouil Platanios (Carnegie Mellon University) · Sujith Ravi (Google Research) · Andrew Tomkins (Google)

Latent distance estimation for random geometric graphs
Ernesto J Araya Valdivia (Université Paris-Sud) · Yohann De Castro (ENPC)

Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network
Jennifer Cardona (Stanford University) · Michael Howland (Stanford University) · John Dabiri (Stanford University)

The Functional Neural Process
Christos Louizos (University of Amsterdam) · Xiahan Shi (Bosch Center for Artificial Intelligence) · Klamer Schutte (TNO) · Max Welling (University of Amsterdam / Qualcomm AI Research)

Recurrent Registration Neural Networks for Deformable Image Registration
Robin Sandkühler (Department of Biomedical Engineering, University of Basel) · Simon Andermatt (Center for medical Image Analysis and Navigation) · Grzegorz Bauman (University of Basel Hospital) · Sylvia Nyilas (Bern University Hospital) · Christoph Jud (University of Basel) · Philippe C. Cattin (University of Basel)

Unsupervised State Representation Learning in Atari
Ankesh Anand (Mila, Université de Montréal) · Evan Racah (Mila, Université de Montréal) · Sherjil Ozair (Université de Montréal) · Yoshua Bengio (Mila) · Marc-Alexandre Côté (Microsoft Research) · R Devon Hjelm (Microsoft Research)

Unlocking Fairness: a Trade-off Revisited
Michael Wick (Oracle Labs) · swetasudha panda (Oracle Labs) · Jean-Baptiste Tristan (Oracle Labs)

Fisher Efficient Inference of Intractable Models
Song Liu (University of Bristol) · Takafumi Kanamori (Tokyo Institute of Technology/RIKEN) · Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems) · Yu Chen (University of Bristol)

Thompson Sampling and Approximate Inference
Kieu-My Phan (University of Massachusetts Amherst) · Yasin Abbasi (Adobe Research) · Justin Domke (University of Massachusetts, Amherst)

PRNet: Self-Supervised Learning for Partial-to-Partial Registration
Yue Wang (MIT) · Justin M Solomon (MIT)

Surrogate Objectives for Batch Policy Optimization in One-step Decision Making
Minmin Chen (Google) · Ramki Gummadi (Google) · Chris Harris (Google) · Dale Schuurmans (University of Alberta & Google Brain)

Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians
Axel Brando (BBVA Data & Analytics and Universitat de Barcelona) · Jose A Rodriguez (BBVA Data & Analytics) · Jordi Vitria (Universitat de Barcelona) · Alberto Rubio Muñoz (BBVA Data & Analytics)

Learning Macroscopic Brain Connectomes via Group-Sparse Factorization
Farzane Aminmansour (University of Alberta) · Andrew Patterson (University of Alberta) · Lei Le (Indiana University Bloomington) · Yisu Peng (Northeastern University) · Daniel Mitchell (University of Alberta) · Franco Pestilli (Indiana University) · Cesar Caiafa (CONICET/RIKEN AIP) · Russell Greiner (University of Alberta) · Martha White (University of Alberta)