ICLR 2019 Accepted Papers

If you are an author on a paper here and your institution is missing, you should immediately update your OpenReview profile and the corresponding profile at https://iclr.cc profile.

Smoothing the Geometry of Probabilistic Box Embeddings
Xiang Li (Department of Computer Science, University of Massachusetts, Amherst) · Luke Vilnis (None) · Dongxu Zhang (University of Massachusetts Amherst) · Michael Boratko (None) · Andrew McCallum (WhizBang Labs)

Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability
Kai Xiao (Massachusetts Institute of Technology) · Vincent Tjeng (Massachusetts Institute of Technology) · Nur Muhammad Shafiullah (Massachusetts Institute of Technology) · Aleksander Madry (MIT)

On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training
Ping Li (Baidu Research) · Phan-Minh Nguyen (Stanford University)

Convolutional Neural Networks on Non-uniform Geometrical Signals Using Euclidean Spectral Transformation
Chiyu Jiang (University of California Berkeley) · Dequan Wang (Fudan University) · Jingwei Huang (Stanford University) · Philip Marcus (None) · Matthias Niessner (Technical University of Munich)

Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
Penghang Yin (UCLA) · Jiancheng Lyu (UC Irvine) · shuai zhang (Qualcomm AI Research) · Stanley J Osher (University of California, Los Angeles) · YINGYONG QI (Qualcomm AI Research) · Jack Xin (UC Irvine)

Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm
Charbel Sakr (University of Illinois, Urbana Champaign) · Naresh Shanbhag (University of Illinois at Urbana-Champaign)

RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks
Xiuyuan Cheng (Duke University) · Qiang Qiu (Duke University) · Robert Calderbank (None) · Guillermo Sapiro (Duke University)

Large Scale Graph Learning From Smooth Signals
Vassilis Kalofolias (Swiss Federal Institute of Technology Lausanne) · Nathanaël Perraudin (ETH Zürich / Swiss Data Science Center)

Deep, Skinny Neural Networks are not Universal Approximators
Jesse Johnson (Sanofi)

L2-Nonexpansive Neural Networks
Haifeng Qian (IBM Research) · Mark N Wegman (International Business Machines)

Generating Liquid Simulations with Deformation-aware Neural Networks
Lukas Prantl (Technische Universität München) · Boris Bonev (Ecole Polytechnique Federale de Lausanne (EPFL)) · Nils Thuerey (Technical University of Munich)

Adversarial Imitation via Variational Inverse Reinforcement Learning
Ahmed H Qureshi (University of California, San Diego) · Byron Boots (Georgia Institute of Technology) · Michael C Yip (UC San Diego)

Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
David Berthelot (Google) · Colin Raffel (Google Brain) · Aurko Roy (Google) · Ian Goodfellow (None)

Learning Localized Generative Models for 3D Point Clouds via Graph Convolution
Diego Valsesia (Politecnico di Torino) · Giulia Fracastoro (Politecnico di Torino) · Enrico Magli (Politecnico di Torino)

Caveats for information bottleneck in deterministic scenarios
Artemy Kolchinsky (Santa Fe Institute) · Brendan D Tracey (Santa Fe Institute / MIT) · Steven Van Kuyk (Victoria University of Wellington)

A Kernel Random Matrix-Based Approach for Sparse PCA
Mohamed El Amine Seddik (CEA) · mohamed Tamaazousti (CEA/LIST/LVIC, The Vision and Content Engineering Laboratory) · Romain Couillet (None)

The relativistic discriminator: a key element missing from standard GAN
Alexia Jolicoeur-Martineau (Mila)

INVASE: Instance-wise Variable Selection using Neural Networks
Jinsung Yoon (University of California, Los Angeles) · James Jordon (University of Oxford) · Mihaela Schaar (None)

Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
Mohammad Kachuee (University of California, Los Angeles (UCLA)) · Orpaz Goldstein (, University of California, Los Angeles) · Kimmo Kärkkäinen (University of California, Los Angeles) · Sajad Darabi (University of California, Los Angeles) · Majid Sarrafzadeh (None)

Adversarial Reprogramming of Neural Networks
Gamaleldin Elsayed (Google Brain) · Ian Goodfellow (None) · Jascha Sohl-Dickstein (Google Brain)

DARTS: Differentiable Architecture Search
Hanxiao Liu (Google Brain) · Karen Simonyan (Google UK) · Yiming Yang (Carnegie Mellon University)

DPSNet: End-to-end Deep Plane Sweep Stereo
Sunghoon Im (KAIST) · Hae-Gon Jeon (Carnegie Mellon University) · Stephen Lin (Microsoft Research) · In Kweon (None)

Preconditioner on Matrix Lie Group for SGD
XI-LIN LI (GMEMS Technologies, Inc.)

Diffusion Scattering Transforms on Graphs
Fernando Gama (University of Pennsylvania) · Alejandro Ribeiro (None) · Joan Bruna (NYU)

Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
Makoto Yamada (Kyoto University / RIKEN) · Yi Wu (Carnegie Mellon University) · Yao Hung Tsai (Carnegie Mellon University) · Hirofumi Ohta (None) · Ruslan Salakhutdinov (None) · Ichiro Takeuchi () · Kenji Fukumizu (Institute of Statistical Mathematics)

Hierarchical interpretations for neural network predictions
Chandan Singh (University of California Berkeley) · William Murdoch (UC Berkeley) · Bin Yu (None)

Dynamic Sparse Graph for Efficient Deep Learning
Liu Liu (UC Santa Barbara) · Lei Deng (UCSB) · Xing Hu (None) · Maohua Zhu (None) · Guoqi Li (Tsinghua University) · Yufei Ding (None) · Yuan Xie (None)

Learning to Understand Goal Specifications by Modelling Reward
Dzmitry Bahdanau (Université de Montréal) · Felix Hill (DeepMind) · Jan Leike (DeepMind) · Edward Hughes () · Arian Hosseini (None) · Pushmeet Kohli (DeepMind) · Edward Grefenstette (Deep Mind)

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
Florian Tramer (Stanford University) · Dan Boneh (None)

Mahsa Baktashmotlagh (None) · Masoud Faraki (Monash University) · Tom Drummond (Monash University) · Mathieu Salzmann (EPFL)

Adversarial Domain Adaptation for Stable Brain-Machine Interfaces
Ali Farshchian (Northwestern University) · Juan Álvaro Gallego (Spanish National Research Council (CSIC)) · Joseph Paul Cohen (Montreal Institute for Learning Algorithms ShortScience.org) · Yoshua Bengio (University of Montreal) · Lee E Miller (Northwestern University) · Sara A Solla (Northwestern University)

Supervised Policy Update for Deep Reinforcement Learning
Quan Vuong (UC San Diego) · Yiming Zhang (Uppsala University) · Keith Ross ()

Differentiable Learning-to-Normalize via Switchable Normalization
Ping Luo (The Chinese University of Hong Kong) · jiamin ren (SenseTime Group Inc.) · zhanglin peng (SenseTime Group Inc.) · Ruimao Zhang (None) · Jingyu Li (SenseTime)

M^3RL: Mind-aware Multi-agent Management Reinforcement Learning
Tianmin Shu (UCLA) · Yuandong Tian (Google [X], Self-driving car)

Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information
Mohit Sharma (Carnegie Mellon University) · Arjun Sharma (CMU, Carnegie Mellon University) · Nicholas Rhinehart (Carnegie Mellon University) · Kris M Kitani (Carnegie Mellon University)

Are adversarial examples inevitable?
Ali Shafahi (University of Maryland) · W. Huang (None) · Christoph Studer (Cornell University) · Soheil Feizi (UMD) · Tom Goldstein (University of Maryland)

An analytic theory of generalization dynamics and transfer learning in deep linear networks
Andrew K Lampinen (University of California Berkeley) · Surya Ganguli (None)

A rotation-equivariant convolutional neural network model of primary visual cortex
Alexander Ecker (University of Tübingen) · Fabian H Sinz (Baylor College of Medicine) · Emmanouil Froudarakis (None) · Paul Fahey (None) · Santiago A Cadena (University of Tuebingen) · Edgar Walker (None) · Erick M Cobos (Baylor College of Medicine) · Jacob Reimer (None) · Andreas Tolias (None) · Matthias Bethge (None)

Nuwan Ferdinand (University of Toronto) · Haider Al-Lawati (Queens University) · Stark Draper (University of Toronto) · Matthew Nokleby (Target Corporation)

Generating Multiple Objects at Spatially Distinct Locations
Tobias Hinz (University of Hamburg) · Stefan Heinrich (University of Hamburg) · Stefan Wermter (University of Hamburg)

Analysis of Quantized Models
LU HOU (Hong Kong University of Science and Technology) · Ruiliang Zhang (TuSimple) · James Kwok (Hong Kong University of Science and Technology)

Context-adaptive Entropy Model for End-to-end Optimized Image Compression
Jooyoung Lee (ETRI) · Seunghyun Cho (Electronics and Telecommunications Research Institute) · Seung-Kwon Beack (Korea Advanced Institute of Science and Technology)

Practical lossless compression with latent variables using bits back coding
James Townsend (University College London) · Thomas Bird (University College London) · David Barber (University College London)

Sample Efficient Imitation Learning for Continuous Control
Fumihiro Sasaki (Ricoh Company, Ltd.)

Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection
Tue Le (AI Research Lab, Trusting Social, Australia) · Tuan Nguyen (AI Research Lab, Trusting Social, Australia) · Trung Le (Deakin University) · Dinh Phung (Monash University) · Paul Montague (None) · Olivier Vel (None) · Lizhen Qu (Data61/CSIRO)

Sample Efficient Adaptive Text-to-Speech
Yutian Chen (DeepMind) · Yannis M Assael (Imperial College London) · Brendan Shillingford (DeepMind) · David Budden (DeepMind) · Scott Reed (Google) · Heiga Zen (Google) · Quan Wang (Google) · Luis C. Cobo (DeepMind) · Andrew Trask (University of Oxford / DeepMind) · Ben Laurie (None) · Caglar Gulcehre (Deepmind) · Aaron van den Oord (Google Deepmind) · Oriol Vinyals (Google DeepMind) · Nando de Freitas (DeepMind)

Distribution-Interpolation Trade off in Generative Models
Damian Leśniak (None) · Igor Sieradzki (Jagiellonian University) · Igor Podolak (Jagiellonian University)

Conditional Network Embeddings
Bo Kang (Ghent University) · Jefrey Lijffijt (University of Bristol) · Tijl De Bie (Ghent University)

Deterministic Variational Inference for Robust Bayesian Neural Networks
Anqi Wu (Princeton University) · Sebastian Nowozin (Microsoft Research) · Ted Meeds (Microsoft Research) · Richard E Turner (University of Cambridge) · José Miguel Hernández Lobato (University of Cambridge) · Alexander Gaunt (Microsoft Research)

Variance Networks: When Expectation Does Not Meet Your Expectations
Kirill Neklyudov (Moscow Institute of Physics and Technology) · Dmitry Molchanov (SAIC-Moscow; Samsung-HSE joint lab) · Arsenii Ashukha (Samsung AI Center) · Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow)

Learning to Remember More with Less Memorization
Hung T Le (Deakin University) · Truyen Tran (Deakin University, Australia) · Svetha Venkatesh (None)

Xingjian Li (Big Data Lab, Baidu Research) · Haoyi Xiong (Missouri University of Science and Technology) · Hanchao Wang (University of Washington, Seattle) · Yuxuan Rao (None) · Liping Liu (None) · Luke Huan (University of North Carolina, Chapel Hill)

signSGD via Zeroth-Order Oracle
Sijia Liu (MIT-IBM Watson AI Lab, IBM Research AI) · Pin-Yu Chen (IBM Research AI) · Xiangyi Chen (University of Minnesota) · Mingyi Hong (University of Minnesota, Minneapolis)

Identifying and Controlling Important Neurons in Neural Machine Translation
David A Bau (Massachusetts Institute of Technology) · Yonatan Belinkov (Harvard / MIT) · Hassan Sajjad (Qatar Computing Research Institute) · Nadir Durrani (QCRI) · Fahim Dalvi (Qatar Computing Research Institute) · James R Glass (None)

Initialized Equilibrium Propagation for Backprop-Free Training
Peter OConnor (University of Amsterdam) · Efstratios Gavves (University of Amsterdam) · Max Welling (Universiteit van Amsterdam & Qualcomm)

Variational Smoothing in Recurrent Neural Network Language Models
Lingpeng Kong (School of Computer Science, Carnegie Mellon University) · Gábor Melis (DeepMind) · Wang Ling (None) · Lei Yu (University of Oxford) · Dani Yogatama (DeepMind)

Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional Clustering
Xiaopeng Li (Department of Computer Science and Engineering, The Hong Kong University of Science and Technology) · Zhourong Chen (The Hong Kong University of Science and Technology) · Leonard Poon (The Education University of Hong Kong) · Nevin Zhang (None)

Reward Constrained Policy Optimization
Chen Tessler (Technion Institute of Technology) · Daniel J Mankowitz (Technion) · Shie Mannor ()

Quaternion Recurrent Neural Networks
Titouan Parcollet (Université d'Avignon) · Mirco Ravanellu (University of Trento) · Mohamed Morchid (Avignon Université) · Georges Linarès (None) · Chiheb Trabelsi (Polytechnique Montréal / MILA) · Renato De Mori (Mc Gill University) · Yoshua Bengio (Mila, University of Montreal)

DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
Xiaodong Gu (Naver) · Kyunghyun Cho (New York University) · Jung-Woo Ha (Clova AI Research, NAVER & LINE) · Sunghun Kim (None)

StrokeNet: A Neural Painting Environment
Ningyuan Zheng (East China Normal University) · Yf Jiang (ECNU) · Dingjiang Huang (East China Normal University)

Large-Scale Study of Curiosity-Driven Learning
Yuri Burda (OpenAI) · Harrison Edwards (OpenAI) · Deepak Pathak (UC Berkeley) · Amos Storkey (University of Edinburgh) · Trevor Darrell (UC Berkeley) · Alexei Efros (UC Berkeley)

Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization
Takayuki Osa (Kyushu Institute of Technology) · Voot Tangkaratt (RIKEN AIP) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers
Alexander (Oleksandr) Shekhovtsov (Czech Technical University in Prague) · Boris Flach (None)

Function Space Particle Optimization for Bayesian Neural Networks
Ziyu Wang (Tsinghua University) · Tongzheng Ren (Tsinghua University) · Jun Zhu (Tsinghua University) · Bo Zhang (None)

Hierarchical Visuomotor Control of Humanoids
Josh Merel (DeepMind) · Arun Ahuja (None) · Vu Pham (None) · Saran Tunyasuvunakool (None) · SIQI LIU (DeepMind) · Dhruva Tirumala Bukkapatnam (DeepMind) · Nicolas Heess (DeepMind) · Greg Wayne (None)

Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds
Peng Cao (Peking University) · Yilun Xu (Peking University) · Yuqing Kong (Peking University) · Yizhou Wang (Peking University)

Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks
José Antonio Oramas Mogrovejo (KU Leuven) · Kaili Wang (KU Leuven) · Tinne Tuytelaars (KU Leuven)

LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
Elke Kirschbaum (Heidelberg University) · Manuel Haussmann (Heidelberg University) · Steffen Wolf (Heidelberg University) · Hannah Sonntag (Heidelberg University) · Justus Schneider (None) · Shehabeldin Elzoheiry (Heidelberg University) · Oliver Kann (University of Heidelberg) · Daniel Durstewitz (Central Institute of Mental Health/ Heidelberg University) · Fred A Hamprecht (None)

Hindsight policy gradients
Paulo Rauber (IDSIA) · Avinash Ummadisingu (Università della Svizzera Italiana) · Filipe Mutz (Instituto Federal do Espirito Santo (IFES)) · Jürgen Schmidhuber (NNAISENSE, Swiss AI Lab IDSIA (USI & SUPSI))

Visual Reasoning by Progressive Module Networks
Seung Wook Kim (University of Toronto) · Makarand Tapaswi (University of Toronto, Vector Institute) · Sanja Fidler ()

Attentive Neural Processes
Hyunjik Kim (DeepMind) · Andriy Mnih (DeepMind) · Jonathan Schwarz (DeepMind) · Marta Garnelo (DeepMind) · S. M. Ali Eslami (DeepMind) · Dan Rosenbaum (DeepMind) · Oriol Vinyals (Google DeepMind) · Yee Whye Teh (None)

RoC-GAN: Robust Conditional GAN
Grigorios Chrysos (Imperial College London) · Jean Kossaifi (Imperial College London) · Stefanos Zafeiriou (None)

Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
Lars Buesing (DeepMind) · Theophane Weber (DeepMind) · Yori Zwols (DeepMind) · Nicolas Heess (DeepMind) · Sebastien Racaniere (None) · Arthur Guez (DeepMind) · Jean-Baptiste Lespiau (DeepMind)

Chao GAO (None) · Jiyi Liu (Yale University) · Yuan Yao (The Hong Kong University of Science and Technology) · Weizhi ZHU (The Hong Kong University of Science and Technology)

Encoding Category Trees Into Word-Embeddings Using Geometric Approach
Tiansi Dong (B-IT, University of Bonn) · Olaf Cremers (None) · Hailong Jin (None) · Juanzi Li (None) · Christian Bauckhage (Fraunhofer IAIS) · Armin Cremers (University of Bonn) · Daniel Speicher (University of Bonn) · Joerg Zimmermann (University of Bonn)

Execution-Guided Neural Program Synthesis
Xinyun Chen (UC Berkeley) · Chang Liu (Electrical Engineering & Computer Science Department, University of California Berkeley) · dawn song (uc berkeley)

Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
Ofir Nachum (Google Brain) · Shixiang Gu (University of Cambridge) · Honglak Lee (Google Brain) · Sergey Levine (UC Berkeley)

Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
Victor Zhong (Salesforce Research) · Caiming Xiong (University of California, Los Angeles) · Nitish Shirish Keskar (Salesforce Research) · richard socher (SalesForce.com and Stanford University)

A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation
Akhilesh Deepak Gotmare (École polytechnique fédérale de Lausanne (EFPL)) · Nitish Shirish Keskar (Salesforce Research) · Caiming Xiong (University of California, Los Angeles) · richard socher (None)

Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
Tiago Ramalho (Cogent Labs) · Marta Garnelo (DeepMind)

On the Turing Completeness of Modern Neural Network Architectures
Jorge Pérez (Universidad de Chile) · Javier Marinković (Universidad de Chile) · Pablo Barceló (None)

Towards the first adversarially robust neural network model on MNIST
Lukas Schott (University of Tuebingen) · Jonas Rauber (University of Tübingen) · Matthias Bethge (None) · Wieland Brendel (University of Tuebingen, Germany)

Evaluating Robustness of Neural Networks with Mixed Integer Programming
Vincent Tjeng (Massachusetts Institute of Technology) · Kai Xiao (Massachusetts Institute of Technology) · Russ Tedrake (MIT)

The Unusual Effectiveness of Averaging in GAN Training
Yasin YAZICI (Nanyang Technological University) · Chuan-Sheng Foo (None) · Stefan Winkler (National University of Singapore) · Kim-Hui Yap (Nanyang Technological University, Singapore) · Georgios Piliouras (Singapore University of Technology and Design) · Vijay Chandrasekhar (None)

Graph Wavelet Neural Network
Bingbing Xu (Institute of Computing Technology, Chinese Academy of Sciences) · Huawei Shen (Institute of Computing Technology, Chinese Academy of Sciences) · Qi Cao (None) · Yunqi Qiu (Nanjing University) · Xueqi Cheng (None)

Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network
Daehyun Ahn (POSTECH) · Dongsoo Lee (Samsung Research) · Taesu Kim (POSTECH) · Jae-Joon Kim (POSTECH)

Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
Yuan Xie (None) · Boyi Liu (Northwestern University) · Qiang Liu (Dartmouth College) · Zhaoran Wang (None) · Yuan Zhou (Indiana University at Bloomington) · Jian Peng (University of Illinois, Urbana Champaign)

Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation
Ehsan Hosseini-Asl (Salesforce Research) · Yingbo Zhou (Salesforce) · Caiming Xiong (University of California, Los Angeles) · richard socher (None)

Meta-Learning For Stochastic Gradient MCMC
Wenbo Gong (University of Cambridge) · Yingzhen Li (University of Cambridge) · José Miguel Hernández Lobato (University of Cambridge)

Efficient Lifelong Learning with A-GEM
Arslan Chaudhry (University of Oxford) · Marc'Aurelio Ranzato (Facebook AI Research) · Marcus Rohrbach (Facebook AI Research) · Mohamed Elhoseiny (Rutgers University)

Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative Models
Eirikur Agustsson (ETH Zurich) · Alexander Sage (None) · Radu Timofte (ETH Zurich) · Luc S.J Van Gool (ETH Zurich)

Learning a SAT Solver from Single-Bit Supervision
Daniel Selsam (Stanford University) · Matthew Lamm (None) · Benedikt B\"{u}nz (None) · Percy Liang (None) · Leonardo Moura (None) · David L Dill (Stanford University)

Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration
Xiaoshuai Zhang (Peking University) · Yiping Lu (Peking University) · Jiaying Liu (None) · Bin Dong (Peking University)

Learning Recurrent Binary/Ternary Weights
Arash Ardakani (McGill University) · Zhengyun Ji (McGill University) · Sean Smithson (None) · Brett Meyer (None) · Warren J Gross (None)

Generative Code Modeling with Graphs
Marc Brockschmidt (Microsoft Research) · Miltiadis Allamanis (Microsoft Research) · Alexander Gaunt (Microsoft Research) · Oleksandr Polozov (Microsoft Research)

Trellis Networks for Sequence Modeling
Shaojie Bai (Carnegie Mellon University) · Zico Kolter (Carnegie Mellon University and Bosch Center for AI) · Vladlen Koltun (Intel Labs)

Meta-Learning Probabilistic Inference for Prediction
Jonathan Gordon (University of Cambridge) · John Bronskill (University of Cambridge) · Matthias Bauer (University of Cambridge, MPI Intelligent Systems) · Sebastian Nowozin (Microsoft Research) · Richard E Turner (University of Cambridge)

Critical Learning Periods in Deep Networks
Alessandro Achille (University of California, Los Angeles) · Matteo Rovere (Brigham and Women's Hospital and Harvard Medical School) · Stefano Soatto (None)

Attention, Learn to Solve Routing Problems!
Wouter Kool (University of Amsterdam ; ORTEC) · Herke van Hoof (McGill University) · Max Welling (Universiteit van Amsterdam & Qualcomm)

Learning to Make Analogies by Contrasting Abstract Relational Structure
Felix Hill (DeepMind) · Adam Santoro (DeepMind) · David GT Barrett (DeepMind) · Ari Morcos (DeepMind) · Timothy Lillicrap (DeepMind & UCL)

Towards Understanding Regularization in Batch Normalization
Ping Luo (The Chinese University of Hong Kong) · Xinjiang Wang (Sensetime Group) · wenqi shao (Sensetime) · Zhanglin Peng (None)

GamePad: A Learning Environment for Theorem Proving
Daniel Huang (University of California Berkeley) · Prafulla Dhariwal (Massachusetts Institute of Technology) · Dawn Song (None) · Ilya Sutskever (OpenAI)

Improving Generalization and Stability of Generative Adversarial Networks
Hoang Thanh-Tung (Deakin University) · Truyen Tran (Deakin University, Australia) · Svetha Venkatesh (None)

The Singular Values of Convolutional Layers
Hanie Sedghi (Google Brain) · Vineet Gupta (Google) · Phil Long (Google)

Yi Chen (Northwestern University) · Jinglin Chen (University of Illinois, Urbana Champaign) · Jing Dong (Columbia University) · Jian Peng (University of Illinois, Urbana Champaign) · Zhaoran Wang (None)

Visceral Machines: Reinforcement Learning with Intrinsic Physiological Rewards
Daniel McDuff (Microsoft Research & AI) · Ashish Kapoor (None)

Small nonlinearities in activation functions create bad local minima in neural networks
Chulhee Yun (MIT) · Suvrit Sra (Massachusetts Institute of Technology) · Ali Jadbabaie (University of Pennsylvania)

ADef: an Iterative Algorithm to Construct Adversarial Deformations
Rima Alaifari (None) · Giovanni S Alberti (University of Genoa) · Tandri Gauksson (ETH Zurich)

code2seq: Generating Sequences from Structured Representations of Code
Uri Alon (Technion) · Shaked Brody (Technion) · Omer Levy (University of Washington) · Eran Yahav (Technion)

Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
Carson Eisenach (Princeton University) · Haichuan Yang (University of Rochester) · Ji Liu (University of Rochester; Kwai Inc.) · Han Liu (None)

Relaxed Quantization for Discretized Neural Networks
Christos Louizos (University of Amsterdam) · Matthias Reisser (University of Amsterdam) · Tijmen Blankevoort (Qualcomm) · Efstratios Gavves (University of Amsterdam) · Max Welling (Universiteit van Amsterdam & Qualcomm)

Sparse Dictionary Learning by Dynamical Neural Networks
Tsung-Han Lin (Intel Labs) · Ping Tak P Tang (Intel Corporation)

PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
Jan Svoboda (Università della Svizzera italiana / NNAISENSE) · Jonathan Masci (Università della Svizzera italiana) · Federico Monti (Università della Svizzera italiana) · Michael Bronstein (Università della Svizzera italiana) · Leonidas Guibas ()

Whitening and Coloring transform for GANs
Aliaksandr Siarohin (University of Trento) · Enver Sangineto (Università di Trento) · Nicu Sebe (University of Trento)

L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data
Jianbo Chen (University of California Berkeley) · Le Song (Ant Financial & Georgia Institute of Technology) · Martin Wainwright (None) · Michael Jordan (University of California, Berkeley)

Deep reinforcement learning with relational inductive biases
Vinicius Zambaldi (DeepMind) · David Raposo (DeepMind) · Adam Santoro (DeepMind) · Victor Bapst (Google DeepMind) · Yujia Li (Google DeepMind) · Igor Babuschkin (None) · Karl Tuyls (DeepMind and University of Liverpool) · David P Reichert (Brown University) · Timothy Lillicrap (DeepMind & UCL) · Edward Lockhart (DeepMind) · Murray Shanahan (DeepMind / Imperial College London) · Victoria Langston (None) · Razvan Pascanu (DeepMind) · Matthew Botvinick (None) · Oriol Vinyals (Google DeepMind) · Peter Battaglia (Google DeepMind)

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
Dan Hendrycks (UC Berkeley) · Thomas Dietterich (Oregon State University)

GO Gradient for Expectation-Based Objectives
Yulai Cong (Duke University) · Miaoyun Zhao (Duke University) · Ke Bai (None) · Lawrence Carin (Duke University)

Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
Marton Havasi (University of Cambridge) · Robert Peharz (University of Cambridge) · José Miguel Hernández Lobato (University of Cambridge)

PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
Jinsung Yoon (University of California, Los Angeles) · James Jordon (University of Oxford) · Mihaela Schaar (None)

Auxiliary Variational MCMC
Raza Habib (University College London) · David Barber (University College London)

KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks
James Jordon (University of Oxford) · Jinsung Yoon (University of California, Los Angeles) · Mihaela Schaar (None)

On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
Nan Lu (The University of Tokyo/ RIKEN-AIP) · Gang Niu (RIKEN AIP) · Aditya K Menon (None) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Approximability of Discriminators Implies Diversity in GANs
Yu Bai (Stanford University) · Tengyu Ma (Facebook) · Andrej Risteski (MIT)

Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers
Yonatan Geifman (Technion) · Guy Uziel (None) · Ran El-Yaniv (Technion and Google)

Namhoon Lee (University of Oxford) · Thalaiyasingam Ajanthan (Australian National University) · Philip H.S Torr (Oxford University)

Deep Graph Infomax
Petar Veličković (DeepMind / University of Cambridge) · William Fedus (University of Montreal) · William L Hamilton (Facebook AI Research) · Pietro Liò (None) · Yoshua Bengio (Mila / U. Montreal) · R Devon Hjelm (Microsoft Research and Mila)

Neural Speed Reading with Structural-Jump-LSTM
Christian Hansen (None) · Casper Hansen (University of Copenhagen) · Stephen Alstrup (University of Copenhagen) · Jakob Simonsen (None) · Christina Lioma (None)

Information Theoretic lower bounds on negative log likelihood
Luis Lastras (International Business Machines)

Equi-normalization of Neural Networks
Pierre Stock (Facebook AI Research) · Benjamin Graham (Facebook) · Rémi Gribonval (Inria) · Hervé Jégou (Facebook AI Research)

LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators
Jianan Li (Beijing Institute of Technology) · Jimei Yang (Adobe Research) · Aaron Hertzmann (Adobe) · Jianming Zhang (Adobe Research) · Tingfa Xu (None)

SGD Converges to Global Minimum in Deep Learning via Star-convex Path
Yi Zhou (Duke University) · Junjie Yang (University of Science and Technology of China) · Huishuai Zhang (Syracuse University) · Yingbin Liang (The Ohio State University) · VAHID TAROKH (DUKE UNIVERSITY)

CEM-RL: Combining evolutionary and gradient-based methods for policy search
Aloïs Pourchot (Gleamer) · Olivier Sigaud (Sorbonne University)

Learning from Positive and Unlabeled Data with a Selection Bias
Masahiro Kato (The University of Tokyo / RIKEN) · Takeshi Teshima (The University of Tokyo / RIKEN) · Junya Honda (The University of Tokyo / RIKEN)

Multi-Domain Adversarial Learning
Alice Schoenauer Sebag (Ministry for the Economy and Finance) · Louise E Heinrich (UCSF) · Marc Schoenauer (INRIA) · Michele Sebag (CNRS, Université Paris-Saclay) · Lani F Wu (University of California, San Francisco) · Steven J Altschuler (University of California at San Francisco)

Overcoming Catastrophic Forgetting via Model Adaptation
Wenpeng Hu (Peking University) · Zhou Lin (None) · Bing Liu (University of Illinois at Chicago) · Chongyang Tao (Peking University) · Jay Tao (Peking University) · Jinwen Ma () · Dongyan Zhao () · Rui Yan ()

Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq Models
Huan Zhang (Shanghai Jiao Tong University) · hai zhao (Shanghai Jiao Tong University)

Learning to Schedule Communication in Multi-agent Reinforcement Learning
Daewoo Kim (KAIST) · Sangwoo Moon (KAIST) · David Earl Hostallero (Korea Advanced Institute of Science and Technology) · Wan Ju Kang (KAIST) · Taeyoung Lee (Korea Advanced Institute of Science and Technology) · Kyunghwan Son (Korea Advanced Institute of Science and Technology) · Yung Yi (KAIST)

Aggregated Momentum: Stability Through Passive Damping
James Lucas (University of Toronto) · Shengyang Sun (University of Toronto) · Richard Zemel (Department of Computer Science, University of Toronto) · Roger Grosse (University of Toronto and Vector Institute)

Learning Factorized Multimodal Representations
Yao Hung Tsai (Carnegie Mellon University) · Paul Pu Liang (Carnegie Mellon University) · Amir Ali Bagherzade (None) · Louis-Philippe Morency (Carnegie Mellon University) · Ruslan Salakhutdinov (None)

Non-vacuous Generalization Bounds at the ImageNet Scale: a PAC-Bayesian Compression Approach
Wenda Zhou (Columbia University) · Victor Veitch (Columbia University) · Morgane Austern (None) · Ryan P Adams (Google) · Peter Orbanz (Columbia University)

Riemannian Adaptive Optimization Methods
Gary Bécigneul (ETH Zürich & MPI Tübingen) · Octavian Ganea (Swiss Federal Institute of Technology)

SOM-VAE: Interpretable Discrete Representation Learning on Time Series
Vincent Fortuin (ETH Zürich) · Matthias Hüser (ETH Zürich) · Francesco Locatello (None) · Heiko Strathmann (Gatsby Unit / ETHZ / Alan Turing Institute) · Gunnar Rätsch ()

Large Scale GAN Training for High Fidelity Natural Image Synthesis
Andrew Brock (Edinburgh Centre for Robotics) · Jeff Donahue (DeepMind) · Karen Simonyan (Google UK)

Improving MMD-GAN Training with Repulsive Loss Function
Wei Wang (University of Melbourne) · Yuan Sun (RMIT University) · Saman Halgamuge (None)

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Robert Geirhos (University of Tübingen) · Patricia Rubisch (None) · Claudio Michaelis (University of Tübingen) · Matthias Bethge (University of Tuebingen) · Felix Wichmann (None) · Wieland Brendel (University of Tuebingen, Germany)

Shengyang Sun (University of Toronto) · Guodong Zhang (University of Toronto & Vector Institute) · Jiaxin Shi (Tsinghua University) · Roger Grosse (University of Toronto and Vector Institute)

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
Yikang Shen (MILA, University of Montreal) · Shawn Tan (University of Montreal) · Alessandro Sordoni (None) · Aaron Courville (Mila, U. Montreal)

Analysing Mathematical Reasoning Abilities of Neural Models
David Saxton (DeepMind) · Edward Grefenstette (Deep Mind) · Felix Hill (DeepMind) · Pushmeet Kohli (DeepMind)

Learning Representations of Sets through Optimized Permutations
Yan Zhang (University of Southampton) · Jonathon Hare (University of Southampton) · Adam Prugel-Bennett (University of Southampton)

Measuring Compositionality in Representation Learning
Jacob Andreas (Berkeley / MS Semantic Machines / MIT)

Detecting Egregious Responses in Neural Sequence-to-sequence Models
Tianxing He (MIT) · James R Glass (None)

Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
Bastian Rieck (ETH Zurich) · Matteo Togninalli (ETH Zurich) · Christian Bock (ETH Zurich) · Michael Moor (ETH Zurich) · Max Horn (ETH Zurich) · Thomas Gumbsch (None) · Karsten Borgwardt (None)

Autoencoder-based Music Translation
Noam Mor (Tel Aviv University) · Lior Wolf (Facebook AI Research) · Adam Polyak (Facebook) · Yaniv Taigman (Facebook AI Research (FAIR))

Fluctuation-dissipation relations for stochastic gradient descent
Sho Yaida (Facebook AI Research)

CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
Florian Mai (Idiap Research Institute) · Lukas Galke (Kiel University) · Ansgar Scherp (University of Essex)

Adaptive Estimators Show Information Compression in Deep Neural Networks
Ivan Chelombiev (University of Bristol) · Conor Houghton (None) · Cian O'Donnell (University of Bristol)

Universal Successor Features Approximators
Diana Borsa (DeepMind) · Andre Barreto (DeepMind) · John Quan (DeepMind) · Daniel J Mankowitz (Technion) · Hado van Hasselt (DeepMind) · Remi Munos (DeepMind) · David Silver (None) · Tom Schaul (DeepMind)

Deep Convolutional Networks as shallow Gaussian Processes
Adrià Garriga-Alonso (University of Cambridge) · Carl Edward Rasmussen (Cambridge University) · Laurence Aitchison (University College London)

Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks
Charbel Sakr (University of Illinois, Urbana Champaign) · Naigang Wang (IBM T. J. Watson Research Center) · Chia-Yu Chen (Stanford University) · Jungwook Choi (IBM Research AI) · Ankur Agrawal (None) · Naresh Shanbhag (University of Illinois at Urbana-Champaign) · Kailash Gopalakrishnan (IBM Research)

On the loss landscape of a class of deep neural networks with no bad local valleys
Quynh Nguyen (Saarland University) · Mahesh Chandra Mukkamala (Saarland University) · Matthias Hein (Saarland University)

h-detach: Modifying the LSTM Gradient Towards Better Optimization
Bhargav Kanuparthi (Montreal Institute for Learning Algorithms) · Devansh Arpit (MILA) · Giancarlo Kerg (Université de Montréal) · Nan Rosemary Ke (MILA, Polytechnique Montreal) · Ioannis Mitliagkas (Mila // University of Montreal) · Yoshua Bengio (Mila / U. Montreal)

Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
Xuanqing Liu (University of California, Davis) · Yao Li (University of California, Davis) · Chongruo Wu (UC Davis) · Cho-Jui Hsieh (UCLA)

Variational Bayesian Phylogenetic Inference
Cheng Zhang (Fred Hutchinson Cancer Research Center) · Frederick A Matsen (Fred Hutchinson Cancer Research Center)

Relational Forward Models for Multi-Agent Learning
Andrea Tacchetti (DeepMind) · Francis Song (DeepMind) · Pedro Mediano (Imperial College) · Vinicius Zambaldi (DeepMind) · János Kramár (Deepmind) · Neil C Rabinowitz (New York University) · Thore Graepel (DeepMind) · Matthew Botvinick (None) · Peter Battaglia (Google DeepMind)

Generative predecessor models for sample-efficient imitation learning
Yannick Schroecker (Georgia Institute of Technology) · Mel Vecerik (None) · Jon Scholz (None)

Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere Convolution
Min Liu (Purdue University) · Fupin Yao (Purdue University) · Chiho Choi (Honda Research Institute USA) · Ayan Sinha (Magic Leap) · Karthik Ramani (Purdue University)

Hyperbolic Attention Networks
Caglar Gulcehre (Maluuba) · Misha Denil ([ERROR]) · Mateusz Malinowski (DeepMind) · Ali Razavi (Deepmind) · Razvan Pascanu (DeepMind) · Karl Moritz Hermann (DeepMind) · Victor Bapst (Google DeepMind) · Victor Bapst (None) · Adam Santoro (DeepMind) · Nando de Freitas (DeepMind)

Structured Neural Summarization
Patrick Fernandes (Microsoft) · Miltiadis Allamanis (Microsoft Research) · Marc Brockschmidt (Microsoft Research)

Multilingual Neural Machine Translation with Knowledge Distillation
Xu Tan (Microsoft Research) · Yi Ren (Zhejiang University) · Di He (Peking University) · Tao Qin (Microsoft Research Asia) · Zhou Zhao (None) · Tie-Yan Liu (Microsoft)

Optimistic mirror descent in saddle-point problems: Going the extra(-gradient) mile
Panayotis Mertikopoulos (CNRS - French National Center for Scientific Research) · Bruno Lecouat (Telecom Paristech) · Houssam Zenati (None) · Chuan-Sheng Foo (None) · Vijay Chandrasekhar (None) · Georgios Piliouras (Singapore University of Technology and Design)

Emergent Coordination Through Competition
SIQI LIU (DeepMind) · Guy Lever (DeepMind) · Nicolas Heess (DeepMind) · Josh Merel (DeepMind) · Saran Tunyasuvunakool (None) · Thore Graepel (DeepMind)

Learning Unsupervised Learning Rules
Luke Metz (Google Brain) · Niru Maheswaranathan (Google Brain) · Brian Cheung (BAIR, UC Berkeley) · Jascha Sohl-Dickstein (Google Brain)

Knowledge Flow: Improve Upon Your Teachers
Iou-Jen Liu (University of Illinois at Urbana-Champaign) · Jian Peng (University of Illinois, Urbana Champaign) · Alex Schwing (University of Illinois, Urbana Champaign)

How Important is a Neuron
Kedar Dhamdhere (None) · Mukund Sundararajan (None) · Qiqi Yan (Google Inc)

Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning
Ignasi Clavera (UC Berkeley) · Anusha Nagabandi (UC Berkeley) · Simin Liu (University of California Berkeley) · Ronald Fearing (None) · Pieter Abbeel (None) · Sergey Levine (UC Berkeley) · Chelsea Finn (University of California Berkeley)

Soft Q-Learning with Mutual-Information Regularization
Jordi Grau-Moya (PROWLER.io) · Felix Leibfried (PROWLER.io) · Peter Vrancx (PROWLER.io)

Representation Degeneration Problem in Training Natural Language Generation Models
Jun Gao (University of Toronto) · Di He (Peking University) · Xu Tan (Microsoft Research) · Tao Qin (Microsoft Research Asia) · Liwei Wang (Peking University) · Tie-Yan Liu (Microsoft)

NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning
Sirui Xie (SenseTime Research) · Junning Huang (SenseTime Research) · Lanxin Lei (Sensetime) · Chunxiao Liu (Sensetime Research) · Zheng Ma (SenseTime Research) · Wei Zhang (None) · Liang Lin (SUN YAT-SEN UNIVERSITY)

Latent Convolutional Models
ShahRukh Athar (Stony Brook University) · Evgeny Burnaev (Skoltech) · Victor Lempitsky (Samsung AI Center Moscow, Skolkovo Institute of Science and Technology)

SNAS: stochastic neural architecture search
Sirui Xie (SenseTime Research) · Hehui Zheng (SenseTime Research) · Chunxiao Liu (Sensetime Research) · Liang Lin (SUN YAT-SEN UNIVERSITY)

Understanding Composition of Word Embeddings via Tensor Decomposition
Abraham Frandsen (Duke University) · Rong Ge (Duke University)

Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces
Senthil Purushwalkam (Carnegie Mellon University) · Abhinav Gupta (None) · Danny Kaufman (None) · Bryan Russell (Adobe)

Stable Opponent Shaping in Differentiable Games
Alistair Letcher (University of Oxford) · Jakob N Foerster (University of Oxford) · David Balduzzi (DeepMind) · Tim Rocktaeschel (Department of Computer Science, University College London) · Shimon Whiteson ()

Learning Robust Representations by Projecting Superficial Statistics Out
Haohan Wang (Carnegie Mellon University) · Zexue He (Beijing Normal University) · Zachary Lipton (Carnegie Mellon University) · Eric P Xing (None)

Yuan Yuan (The Hong Kong University of Science and Technology) · Yueming Lyu (University of Technology Sydney) · Xi SHEN (Ecole des Ponts ParisTech) · Ivor Wai-Hung Tsang (University of Technology Sydney) · Dit-Yan Yeung (Hong Kong University of Science and Technology)

signSGD with Majority Vote is Communication Efficient and Fault Tolerant
Jeremy Bernstein (California Institute of Technology) · Jiawei Zhao (Caltech) · Kamyar Azizzadenesheli (UCI-Caltech) · Anima Anandkumar (Caltech)

DeepOBS: A Deep Learning Optimizer Benchmark Suite
Frank Stefan Schneider (University of Tuebingen) · Lukas Balles (University of Tübingen) · Philipp Hennig (Max Planck Institute for Intelligent Systems, Max-Planck Institute)

Policy Transfer with Strategy Optimization
Wenhao Yu (Georgia Institute of Technology) · C. Liu (None) · Greg Turk (Georgia Institute of Technology)

Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Chih-Yao Ma (Georgia Institute of Technology) · jiasen lu (Georgia Institute of Technology) · Zuxuan Wu (University of Maryland, College Park) · Ghassan AlRegib (Georgia Tech) · Zsolt Kira (Georgia Tech) · richard socher (None) · Caiming Xiong (University of California, Los Angeles)

RNNs implicitly implement tensor-product representations
Tom McCoy (Johns Hopkins University) · Tal Linzen (Johns Hopkins University) · Ewan Dunbar (CNRS / Université Paris Diderot) · Paul Smolensky (University of Colorado, Boulder)

Neural network gradient-based learning of black-box function interfaces
Alon Jacovi (IBM Research) · guy hadash (Technion) · Einat Kermany (IBM Research AI) · Boaz Carmeli (IBM Research - Haifa) · Ofer Lavi (IBM Research AI) · George M. Kour (IBM Research Lab) · Jonathan Berant (Google)

Structured Adversarial Attack: Towards General Implementation and Better Interpretability
KAIDI XU (Northeastern University) · Sijia Liu (MIT-IBM Watson AI Lab, IBM Research AI) · Pu Zhao (None) · Pin-Yu Chen (IBM Research AI) · Huan Zhang (UC Davis) · Quanfu Fan (IBM Research) · Deniz Erdogmus (None) · Yanzhi Wang (None) · Xue Lin (Northeastern University)

Integer Networks for Data Compression with Latent-Variable Models
Johannes Ballé (Google) · Nick Johnston (Google) · David Minnen (Google)

Kernel RNN Learning (KeRNL)
Christopher Roth (University of Texas at Austin) · Ingmar Kanitscheider (OpenAI) · Ila Fiete (None)

Residual Non-local Attention Networks for Image Restoration
Yulun Zhang (Northeastern University) · Kunpeng Li (Northeastern University) · Kai Li (Northeastern University) · Bineng Zhong (Huaqiao University) · Yun Fu (Northeastern University)

Wizard of Wikipedia: Knowledge-Powered Conversational Agents
Emily Dinan (Facebook AI Research) · Stephen Roller (Facebook AI Research) · Kurt Shuster (Facebook AI Research) · Angela Fan (LORIA) · Michael Auli (Facebook AI Research) · Jason Weston (Facebook AI Research)

Invariant and Equivariant Graph Networks
Haggai Maron (Weizmann Institute of Science) · Heli Ben-Hamu (Weizmann Institute of Science) · Nadav Shamir (None) · Yaron Lipman (Weizmann Institute of Science)

Generalized Tensor Models for Recurrent Neural Networks
Valentin Khrulkov (Skolkovo Institute of Science and Technology) · Oleksii Hrinchuk (Skolkovo Institute of Science and Technology) · Ivan Oseledets (Skolkovo Institute of Science and Technology)

Learning deep representations by mutual information estimation and maximization
R Devon Hjelm (Microsoft Research and Mila) · Alex Fedorov (The Mind Research Network) · Samuel Lavoie-Marchildon (University of Montreal) · Karan Grewal (University of Toronto) · Philip Bachman (Microsoft Research) · Adam Trischler (Toronto University) · Yoshua Bengio (Mila / U. Montreal)

Information-Directed Exploration for Deep Reinforcement Learning
Nikolay Nikolov (Imperial College London) · Johannes Kirschner (ETH Zurich) · Felix Berkenkamp (ETH Zurich) · Andreas Krause (Swiss Federal Institute of Technology)

Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs
Sachin Kumar (Carnegie Mellon University) · Yulia Tsvetkov (Computer Science Department, Stanford University)

Bayesian Policy Optimization for Model Uncertainty
Gilwoo Lee (Carnegie Mellon University) · Brian Hou (University of Washington) · Aditya Mandalika (None) · Jeongseok Lee (Seoul National University) · Siddhartha Srinivasa (None)

Gradient Descent Provably Optimizes Over-parameterized Neural Networks
Simon Du (Carnegie Mellon University) · Xiyu Zhai (Massachusetts Institute of Technology) · Barnabás Póczos (None) · Aarti Singh (Carnegie Mellon University)

Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods
Apratim Bhattacharyya (Max Planck Institute for Informatics) · Mario Fritz (Max Planck Institute for Informatics) · Bernt Schiele (MPI Informatics)

Episodic Curiosity through Reachability
Nikolay Savinov (ETH Zurich) · Anton Raichuk (Google) · Damien Vincent (Google) · Raphaël Marinier (Google) · Marc Pollefeys (ETH Zurich / Microsoft) · Timothy Lillicrap (DeepMind & UCL) · Sylvain Gelly ()

From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference
Randall Balestriero (RIce University) · Richard Baraniuk (Rice University)

A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs
Jack Lindsey (Stanford University) · Samuel Ocko (None) · Surya Ganguli (None) · Stephane Deny (Pierre and Marie Curie University, Paris, France)

Learning-Based Frequency Estimation Algorithms
Chen-Yu Hsu (CSAIL, MIT) · Piotr Indyk (MIT) · Dina Katabi (None) · Ali Vakilian (Massachusetts Institute of Technology)

Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
Vaishnavh Nagarajan (Carnegie Mellon University) · Zico Kolter (Carnegie Mellon University and Bosch Center for AI)

Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer
Hsueh-Ti Derek Liu (University of Toronto) · Michael Tao (Toronto University) · Chun-Liang Li (Machine Learning Department, Carnegie Mellon University) · Derek Nowrouzezahrai (McGill University) · Alec Jacobson (University of Toronto)

Dynamic Channel Pruning: Feature Boosting and Suppression
Xitong Gao (Shenzhen Institutes of Advanced Technology) · Yiren Zhao (University of Cambridge) · Łukasz Dudziak (University of Cambridge) · Robert Mullins (University of Cambridge) · Cheng-zhong Xu (None)

Solving the Rubik's Cube with Approximate Policy Iteration
Stephen McAleer (University of California, Irvine) · Forest Agostinelli (University of California, Irvine) · Alexander K Shmakov (None) · Pierre Baldi (UCI)

Diversity is All You Need: Learning Skills without a Reward Function
Benjamin Eysenbach (CMU, Google) · Abhishek Gupta (UC Berkeley) · Julian Ibarz (google.com) · Sergey Levine (UC Berkeley)

Unsupervised Hyper-alignment for Multilingual Word Embeddings
Jean Alaux-Lorain (Ecole Normale Supérieure) · Edouard Grave (Columbia University) · marco cuturi (Google Inc.) · Armand Joulin (Facebook AI Research)

Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation
Sang-Woo Lee (Clova AI Research, Naver Corp.) · Tong Gao (None) · Sohee Yang (Clova AI Research, NAVER Corp.) · Jaejun Yoo (NAVER Corp.) · Jung-Woo Ha (Clova AI Research, NAVER & LINE)

Multi-class classification without multi-class labels
Yen-Chang Hsu (Georgia Institute of Technology) · Zhaoyang Lv (Georgia Institute of Technology) · Joel Schlosser (None) · Phillip Odom (None) · Zsolt Kira (Georgia Tech)

Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach
Minhao Cheng (University of California, Los Angeles) · Thong M Le (University of California Davis) · Pin-Yu Chen (IBM Research AI) · Huan Zhang (UCLA) · Jinfeng Yi (None) · Cho-Jui Hsieh (UCLA)

Recurrent Experience Replay in Distributed Reinforcement Learning
Steven Kapturowski (Apple) · Georg Ostrovski (DeepMind) · John Quan (DeepMind) · Remi Munos (DeepMind) · Will Dabney (Amazon)

Unsupervised Learning via Meta-Learning
Kyle Hsu (University of Toronto) · Sergey Levine (UC Berkeley) · Chelsea Finn (University of California Berkeley)

Discriminator Rejection Sampling
Samaneh Azadi (UC Berkeley) · Catherine Olsson (New York University) · Trevor Darrell (UC Berkeley) · Ian Goodfellow (None) · Augustus Odena (google)

AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
Bo Chang (University of British Columbia) · Minmin Chen (Google) · Eldad Haber (None) · Ed H. Chi (Google AI)

Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality
Taiji Suzuki (The University of Tokyo / RIKEN-AIP)

Excessive Invariance Causes Adversarial Vulnerability
Joern-Henrik Jacobsen (Vector Institute and University of Toronto) · Jens Behrmann (University of Bremen) · Richard Zemel (Department of Computer Science, University of Toronto) · Matthias Bethge (University of Tuebingen)

Jacob Menick (Reed College) · Nal Kalchbrenner (Google Brain Amsterdam)

Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
Ilya Kostrikov (New York University) · Kumar Agrawal (Google AI) · Debidatta Dwibedi (Google) · Sergey Levine (None) · Jonathan Tompson (Google Brain)

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
Stanislaw Jastrzebski (Jagiellonian University) · Zachary Kenton (Oxford Applied and Theoretical Machine Learning group) · Nicolas Ballas (Facebook AI Research) · Asja Fischer (Ruhr-Universität Bochum) · Yoshua Bengio (Mila / U. Montreal) · Amos Storkey (University of Edinburgh)

The Laplacian in RL: Learning Representations with Efficient Approximations
Yifan Wu (Carnegie Mellon University) · George Tucker (Google Brain) · Ofir Nachum (Google Brain)

A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery
Ali Mousavi (Google AI) · Gautam Dasarathy (Arizona State University) · Richard Baraniuk (Rice University)

Adversarial Audio Synthesis
Chris Donahue (UC San Diego) · Julian McAuley (None) · Miller Puckette ()

Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
Michael Lutter (TU Darmstadt) · Christian Ritter (TU Darmstadt) · Jan Peters (TU Darmstadt & MPI for Intelligent Systems)

Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
Chun-Fu (Richard) Chen (IBM Research) · Quanfu Fan (IBM Research) · Neil R Mallinar (IBM) · Tom Sercu (IBM Research AI) · Rogerio Feris (IBM Research AI)

On Computation and Generalization of Generative Adversarial Networks under Spectrum Control
Haoming Jiang (Georgia Institute of Technology) · Zhehui Chen (Georgia Institute of Technology) · Minshuo Chen (Georgia Institute of Technology) · Feng Liu (None) · Dingding Wang (None) · Tuo Zhao (Georgia Tech)

Quasi-hyperbolic momentum and Adam for deep learning
Jerry Ma (Facebook AI Research) · Denis Yarats (Facebook AI Reserach)

Deep Frank-Wolfe For Neural Network Optimization
Leonard Berrada (University of Oxford) · Andrew Zisserman (University of Oxford) · M. Pawan Kumar (University of Oxford)

No Training Required: Exploring Random Encoders for Sentence Classification
John F Wieting (None) · Douwe Kiela (University of Cambridge)

Measuring and regularizing networks in function space
Ari S Benjamin (University of Pennsylvania) · David Rolnick (University of Pennsylvania) · Konrad P Kording (University of Pennsylvania)

Learning Finite State Representations of Recurrent Policy Networks
Anurag Koul (Oregon State University) · Alan Fern (None) · Samuel Greydanus (Google AI)

Analyzing Inverse Problems with Invertible Neural Networks
Lynton Ardizzone (Heidelberg University) · Jakob Kruse (Heidelberg University) · Carsten Rother (None) · Ullrich Koethe (Heidelberg University)

AutoLoss: Learning Discrete Schedule for Alternate Optimization
Haowen Xu (CMU) · Hao Zhang (Shanghai Jiao Tong University) · Zhiting Hu (None) · Xiaodan Liang (Carnegie Mellon University) · Ruslan Salakhutdinov (None) · Eric Xing (None)

On Self Modulation for Generative Adversarial Networks
Ting Chen (UCLA) · Mario Lucic (Google AI (Brain Team)) · Neil Houlsby (Google) · Sylvain Gelly ()

Spectral Inference Networks: Unifying Deep and Spectral Learning
David Pfau (DeepMind) · Stig Petersen (DeepMind) · Ashish Agarwal (Google) · David GT Barrett (DeepMind) · Kimberly L Stachenfeld (DeepMind)

How Powerful are Graph Neural Networks?
Keyulu Xu (MIT) · Weihua Hu (Stanford University) · Jure Leskovec (Stanford University) · Stefanie Jegelka (MIT)

Learning Two-layer Neural Networks with Symmetric Inputs
Rong Ge (Duke University) · Rohith Kuditipudi (Duke University) · Zhize Li (None) · Xiang Wang (Duke University)

Neural Probabilistic Motor Primitives for Humanoid Control
Josh Merel (DeepMind) · Leonard Hasenclever (Deepmind) · Alexandre Galashov (DeepMind) · Arun Ahuja (None) · Vu Pham (None) · Greg Wayne (None) · Yee Whye Teh (None) · Nicolas Heess (DeepMind)

The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure
Frederic Koehler (MIT) · Andrej Risteski (MIT)

Phase-Aware Speech Enhancement with Deep Complex U-Net
Hyeong-Seok Choi (Seoul National University) · Jang-Hyun Kim (Seoul National University) · Jaesung Huh (Seoul National University) · Adrian Kim (Naver) · Jung-Woo Ha (Clova AI Research, NAVER & LINE) · Kyogu Lee (Seoul National University)

Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation
Soochan Lee (Seoul National University) · Junsoo Ha (Hanyang University) · Gunhee Kim (Seoul National University, rippleAI)

Learning Multimodal Graph-to-Graph Translation for Molecule Optimization
Wengong Jin (Massachusetts Institute of Technology) · Kevin Yang (MIT) · Regina Barzilay (None) · Tommi Jaakkola (MIT)

Modeling Parts, Structure, and System Dynamics via Predictive Learning
Zhenjia Xu (Shanghai Jiao Tong University) · Zhijian Liu (MIT) · Chen Sun (Google) · Kevin Murphy (None) · William Freeman (MIT and Google) · Joshua B Tenenbaum (None) · Jiajun Wu (MIT)

Scalable Unbalanced Optimal Transport using Generative Adversarial Networks
Karren Yang (Massachusetts Institute of Technology) · Caroline Uhler (Massachusetts Institute of Technology)

ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary Networks
Mingzhang Yin (UT Austin) · Mingyuan Zhou (UT Austin)

Deep Layers as Stochastic Solvers
Adel Bibi (KAUST / Intel Labs) · Bernard Ghanem (King Abdullah University of Science and Technology) · Vladlen Koltun (Intel Labs) · Rene Ranftl (Intel Labs)

Graph HyperNetworks for Neural Architecture Search
Chris Zhang (University of Waterloo, University of Waterloo) · Mengye Ren (Uber ATG / University of Toronto) · Raquel Urtasun (Department of Computer Science, University of Toronto)

Learning Self-Imitating Diverse Policies
Tanmay Gangwani (University of Illinois, Urbana Champaign) · Qiang Liu (Dartmouth College) · Jian Peng (University of Illinois, Urbana Champaign)

Slimmable Neural Networks
Jiahui Yu (University of Illinois at Urbana Champaign) · Linjie Yang (None) · Ning Xu (Snap Research) · Jianchao Yang (Bytedance Inc) · Thomas Huang (None)

BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Maxime Chevalier-Boisvert (Mila) · Dzmitry Bahdanau (Université de Montréal) · Salem Lahlou (Universite de Montreal - MILA) · Lucas Willems (Ecole Normale Supérieure de Paris) · Chitwan Saharia (Indian Institute of Technology, Bombay) · Thien H Nguyen (University of Oregon) · Yoshua Bengio (University of Montreal)

Complement Objective Training
Hao-Yun Chen (National Tsing Hua University) · Pei-Hsin Wang (National Tsing Hua University) · Chun-Hao Liu (National Tsing Hua University) · Shih-Chieh Chang (None) · Jia-Yu Pan (Google AI) · Yu-Ting Chen (None) · Wei Wei (Google AI) · Da-Cheng Juan (Google Research)

ProMP: Proximal Meta-Policy Search
Jonas Rothfuss (UC Berkeley / Karlsruhe Institute of Technology) · Dennis Lee (University of California Berkeley) · Ignasi Clavera (UC Berkeley) · Tamim Asfour (Karlsruhe Institute of Technology) · Pieter Abbeel (UC Berkeley / Embodied Intelligence)

Hierarchical Reinforcement Learning with Hindsight
Andrew Levy (Brown University) · Kate Saenko (Boston University) · Kate Saenko (None)

Discovery of natural language concepts in individual units
Seil Na (Seoul National University) · Yo Joong Choe (Kakao, Carnegie Mellon University) · Dong-Hyun Lee (Kakao Brain) · Gunhee Kim (Seoul National University, rippleAI)

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
Thomas Miconi (Uber AI Labs) · Aditya Rawal (Uber AI Labs) · Jeff Clune (Uber AI Labs) · Kenneth O. Stanley (Uber AI Labs)

A2BCD: Asynchronous Acceleration with Optimal Complexity
Robert R Hannah (University of California, Los Angeles) · Fei Feng (University of California, Los Angeles) · Wotao Yin (None)

A Systematic Study of Binary Neural Networks' Optimisation
Milad Alizadeh (University of Oxford) · Javier Fernández Marqués (University of Oxford) · Nicholas Lane (University of Oxford and Samsung AI) · Yarin Gal (University of Oxford)

Universal Transformers
Mostafa Dehghani (University of Amsterdam) · Stephan Gouws (DeepMind) · Oriol Vinyals (Google DeepMind) · Jakob Uszkoreit (Google) · Lukasz Kaiser (Google)

Yanbin Liu (University of Technology Sydney) · Juho Lee (University of Oxford) · Minseop Park (None) · Saehoon Kim (AITRICS) · Eunho Yang (Korea Advanced Institute of Science and Technology) · Sung Ju Hwang (KAIST) · Yi Yang (None)

Improving Sequence-to-Sequence Learning via Optimal Transport
Liqun Chen (Duke University) · Yizhe Zhang (Duke University) · Ruiyi Zhang (Duke University) · Chenyang Tao (Duke University) · Zhe Gan (Microsoft) · Haichao Zhang (Baidu USA) · Bai Li (Duke University) · Dinghan Shen (Peking University) · Changyou Chen (SUNY Buffalo) · Lawrence Carin (Duke University)

Verification of Non-Linear Specifications for Neural Networks
Chongli Qin (DeepMind) · Krishnamurthy Dvijotham (DeepMind) · Brendan ODonoghue (Stanford University) · Rudy R Bunel (University of Oxford) · Robert W Stanforth (DeepMind) · Sven Gowal (DeepMind) · Jonathan Uesato (Deepmind) · Grzegorz M Swirszcz (International Business Machines T.J. Watson Center) · Pushmeet Kohli (DeepMind)

Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
Curtis Hawthorne (Google Brain) · Andriy Stasyuk (None) · Adam Roberts (Google Brain) · Ian Simon (Google) · Anna Huang (Google) · Sander Dieleman (DeepMind) · Erich K Elsen (Stanford University) · Jesse Engel (Google Brain) · Douglas Eck (Google Brain)

Variational Autoencoders with Jointly Optimized Latent Dependency Structure
Jiawei He (Simon Fraser University) · Yu Gong (Simon Fraser University) · Joe Marino (Caltech) · Greg Mori (Borealis AI / SFU) · Andreas Lehrmann (Facebook)

A comprehensive, application-oriented study of catastrophic forgetting in DNNs
Benedikt Pfülb (Hochschule Fulda) · Alexander Gepperth (University of Applied Sciences Fulda)

Efficient Training on Very Large Corpora via Gramian Estimation
Walid Krichene (Google) · Nicolas E Mayoraz (Google) · Steffen Rendle (Google Research) · Li Zhang (Google) · Xinyang Yi (Google) · Lichan Hong (Google Brain) · Ed H. Chi (Google AI) · John Anderson (None)

Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
Roman Novak (Google Brain) · Lechao Xiao (Google Brain) · Yasaman Bahri (Google Brain) · Jaehoon Lee (Google Brain) · Greg Yang (Microsoft Research) · Daniel Abolafia (Google Brain) · Jeffrey Pennington (Google Brain) · Jascha Sohl-Dickstein (Google Brain)

Unsupervised Domain Adaptation for Distance Metric Learning
Kihyuk Sohn (NEC Laboratories America) · Wenling Shang (University of Amsterdam) · Xiang Yu (NEC Laboratories America) · Manmohan Chandraker (UCSD, NEC Labs)

Learning to Represent Edits
Pengcheng Yin (Carnegie Mellon University) · Graham Neubig (Carnegie Mellon University) · Miltiadis Allamanis (Microsoft Research) · Marc Brockschmidt (Microsoft Research) · Alexander Gaunt (Microsoft Research)

Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning
Ying Wen (UCL) · Yaodong Yang (UCL) · Rui Luo (None) · Jun Wang (UCL) · Wei Pan (TU Delft)

Decoupled Weight Decay Regularization
Ilya Loshchilov (University of Freiburg) · Frank Hutter (University of Freiburg)

Generative Question Answering: Learning to Answer the Whole Question
Mike Lewis (None) · Angela Fan (LORIA)

Hierarchical Generative Modeling for Controllable Speech Synthesis
Wei-Ning Hsu (Massachusetts Institute of Technology) · Yu Zhang (Google Brain) · Ron Weiss (Google) · Heiga Zen (Google) · Yonghui Wu (None) · Yuxuan Wang (ByteDance, Inc.) · Yuan Cao (Google Brain) · Ye Jia (Google) · Zhifeng Chen (None) · Jonathan Shen (Google) · Patrick Nguyen (Google) · Ruoming Pang (Google Inc.)

Exploration by random network distillation
Yuri Burda (OpenAI) · Harrison Edwards (University of Edinburgh) · Amos Storkey (University of Edinburgh) · Oleg Klimov (None)

FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models
Will Grathwohl (Department of Computer Science, University of Toronto) · Tian Qi Chen (UofT) · Jesse Bettencourt (University of Toronto) · Ilya Sutskever (OpenAI) · David Duvenaud (University of Toronto)

Learning concise representations for regression by evolving networks of trees
William La Cava (University of Pennsylvania) · Tilak Raj Singh (School of Engineering and Applied Science, University of Pennsylvania) · Srinivas Suri (University Of Pennsylvania) · Srinivas Suri (None)

Diversity and Depth in Per-Example Routing Models
Prajit Ramachandran (Google Brain) · Quoc V Le (Google)

Feature Intertwiner for Object Detection
Hongyang Li (The Chinese University of Hong Kong) · Bo Dai (The Chinese University of Hong Kong) · Shaoshuai Shi (The Chinese University of Hong Kong) · Wanli Ouyang (None) · Xiaogang Wang (None)

Optimal Completion Distillation for Sequence Learning
Sara Sabour (Google Brain) · William Chan (Carnegie Mellon University) · Mohammad Norouzi (Google Brain)

ProxQuant: Quantized Neural Networks via Proximal Operators
Yu Bai (Stanford University) · Yu-Xiang Wang (UC Santa Barbara) · Edo Liberty (None)

Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
Amanpreet Singh (New York University) · Tushar Jain (New York University) · Sainbayar Sukhbaatar (New York University)

Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching
Chih-Kuan Yeh (Carnegie Mellon University) · Jianshu Chen (Tencent AI Lab) · Chengzhu Yu (None) · Dong Yu (None)

Generalizable Adversarial Training via Spectral Normalization
Farzan Farnia (Stanford University) · Jesse M Zhang (Stanford University) · David Tse (None)

Wasserstein Barycenter Model Ensembling
Pierre Dognin (International Business Machines) · Igor Melnyk (IBM) · Jarret Ross (IBM Research AI) · Cicero Nogueira dos Santos (IBM Research) · Youssef Mroueh (IBM Research AI) · Tom Sercu (IBM Research AI)

Learning Entropic Wasserstein Embeddings
Charlie Frogner (Massachusetts Institute of Technology) · Farzaneh Mirzazadeh (MIT-IBM Watson AI Lab, IBM Research) · Justin Solomon (Princeton University)

Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer
Ori Press (Tel Aivv University) · Tomer Galanti (Tel Aviv University) · Sagie Benaim (Tel Aviv University) · Lior Wolf (Facebook AI Research)

Transfer and Exploration via the Information Bottleneck
Anirudh Goyal Alias Parth Goyal (MILA, University of Montreal) · Riashat Islam (McGill University (RLLab)) · DJ Strouse (DeepMind) · Zafarali Ahmed (McGill University) · Hugo Larochelle (Google Brain) · Matthew Botvinick (None) · Sergey Levine (UC Berkeley) · Yoshua Bengio (Mila, University of Montreal)

Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds
Cenk Baykal (Massachusetts Institute of Technology) · Lucas Liebenwein (Massachusetts Institute of Technology) · Igor Gilitschenski (Massachusetts Institute of Technology) · Dan Feldman (None) · Daniela Rus (MIT)

Learning to Describe Scenes with Programs
Yunchao Liu (Tsinghua University) · Zheng Wu (Shanghai Jiao Tong University) · Daniel Ritchie (Brown University) · William Freeman (MIT and Google) · Joshua B Tenenbaum (None) · Jiajun Wu (MIT)

InstaGAN: Instance-aware Image-to-Image Translation
Sangwoo Mo (KAIST) · Minsu Cho (POSTECH) · Jinwoo Shin (None)

DOM-Q-NET: Grounded RL on Structured Language
Sheng Jia (University of Toronto) · Jamie Kiros (Google) · Jimmy Ba (None)

A new dog learns old tricks: RL finds classic optimization algorithms
Weiwei Kong (Georgia Institute of Technology) · Christopher Liaw (University of British Columbia) · Aranyak Mehta (Google Research) · D. Sivakumar (Google Research)

The Deep Weight Prior
Andrei Atanov (National Research University Higher School of Economics) · Arsenii Ashukha (Samsung AI Center) · Kirill Struminsky (None) · Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow) · Max Welling (Universiteit van Amsterdam & Qualcomm)

Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
Ryan Murphy (Purdue University) · Balasubramaniam Srinivasan (Purdue University) · Vinayak Rao (None) · Bruno Ribeiro (Purdue University)

Variational Autoencoder with Arbitrary Conditioning
Oleg Ivanov (Samsung AI Center) · Mikhail Figurnov (DeepMind) · Dmitry P. Vetrov (Higher School of Economics, Samsung AI Center, Moscow)

ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
Wei Ping (UC Irvine) · Kainan Peng (Carnegie Mellon University) · Jitong Chen (ByteDance)

From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
Justin Fu (University of California Berkeley) · Anoop Korattikara Balan (Google Research) · Sergey Levine (UC Berkeley) · Sergio Guadarrama (Google AI)

Human-level Protein Localization with Convolutional Neural Networks
Elisabeth Rumetshofer (LIT AI Lab, JKU Linz) · Markus Hofmarcher (Johannes Kepler University Linz) · Clemens Röhrl (None) · Sepp Hochreiter (Johannes Kepler University Linz) · Günter Klambauer (Johannes Kepler University Linz)

Neural Program Repair by Jointly Learning to Localize and Repair
Marko Vasic (The University of Texas at Austin) · Aditya Kanade (Google Brain & Indian Institute of Science) · Petros Maniatis (Google Brain) · David Bieber (Google Brain) · Rishabh Singh (Google Brain)

Pankaj Gupta (University of Munich (LMU) and Siemens AG) · Yatin Chaudhary (Technical University Munich) · Florian Buettner (Hemlholtz Zentrum München) · Hinrich Schuetze (None)

Learning Protein Structure with a Differentiable Simulator
John B Ingraham (Harvard University) · Adam J Riesselman (Harvard University) · Chris Sander (Harvard Medical School) · Debora Marks (Harvard University)

Local SGD Converges Fast and Communicates Little
Sebastian Stich (EPFL)

Amortized Bayesian Meta-Learning
Sachin Ravi (Princeton University) · Alex Beatson (Princeton University)

Sliced Wasserstein Auto-Encoders
Soheil Kolouri (HRL Laboratories) · Phil Pope (HRL Laboratories) · Charles Martin (None) · Gustavo Rohde (None)

AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods
Zhiming Zhou (Shanghai Jiao Tong University) · Qingru Zhang (Shanghai Jiao Tong University) · Guansong Lu (Shanghai Jiao Tong University) · Hongwei Wang (Shanghai Jiao Tong University) · Weinan Zhang (Shanghai Jiao Tong University) · Yong Yu (None)

Visual Semantic Navigation using Scene Priors
Wei Yang (The Chinese University of Hong Kong) · Xiaolong Wang (Carnegie Mellon University) · Ali Farhadi (None) · Abhinav Gupta (None) · Roozbeh Mottaghi (Allen Institute for AI)

Meta-Learning with Latent Embedding Optimization
Andrei Rusu (DeepMind) · Dushyant Rao (DeepMind) · Jakub Sygnowski (Uniwersytet Warszawski) · Oriol Vinyals (Google DeepMind) · Razvan Pascanu (DeepMind) · Simon Osindero (DeepMind) · Raia Hadsell (DeepMind)

Multilingual Neural Machine Translation With Soft Decoupled Encoding
Xinyi Wang (School of Computer Science, Carnegie Mellon University) · Hieu Pham (Carnegie Mellon University) · Philip Arthur (Nara Institute of Science and Technology, Japan) · Graham Neubig (Carnegie Mellon University)

Learning To Simulate
Nataniel Ruiz (Boston University) · Samuel Schulter (NEC-Labs) · Manmohan Chandraker (UCSD, NEC Labs)

Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
Kenneth Marino (Carnegie Mellon University) · Abhinav Gupta (None) · Rob Fergus () · Arthur Szlam (Facebook)

Gradient descent aligns the layers of deep linear networks
Ziwei Ji (University of Illinois at Urbana-Champaign) · Matus Telgarsky (University of Illinois, Urbana-Champaign)

On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization
Xiangyi Chen (University of Minnesota) · Sijia Liu (MIT-IBM Watson AI Lab, IBM Research AI) · Ruoyu Sun (University of Illinois Urbana-Champaign) · Mingyi Hong (University of Minnesota, Minneapolis)

The role of over-parametrization in generalization of neural networks
Behnam Neyshabur (New York University) · Zhiyuan Li (Department of Computer Science, Princeton University) · Srinadh Bhojanapalli (Google Research) · Yann LeCun (None) · Nathan Srebro (TTIC)

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
Jiayuan Mao (MIT CSAIL) · Chuang Gan (MIT/MIT-IBM Watson AI Lab) · Pushmeet Kohli (DeepMind) · Joshua B Tenenbaum (None) · Jiajun Wu (MIT)

Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors
Vitalii Zhelezniak (Babylon Health) · Aleksandar D Savkov (Babylon Health) · April Shen (Babylon Health) · Francesco Moramarco (Babylon Health) · Jack Flann (None) · Nils Hammerla (Babylon Health)

A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks
Sanjeev Arora (Princeton University and Institute for Advanced Study) · Nadav Cohen (Institute for Advanced Study) · Noah Golowich (Harvard University) · Wei Hu (Princeton University)

MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
Xuezhe Ma (School of Computer Science, Carnegie Mellon University) · Chunting Zhou (Carnegie Mellon University) · Eduard Hovy (None)

CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild
Yang Zhang (University of Central Florida) · Hassan Foroosh (University of Central Florida) · Phiip David (U.S. Army Research Laboratory) · Boqing Gong (Tencent AI Lab at Seattle)

Deep learning generalizes because the parameter-function map is biased towards simple functions
Guillermo Valle-Perez (University of Oxford) · Chico Q. Camargo (University of Oxford) · Ard Louis (University of Oxford)

Temporal Difference Variational Auto-Encoder
Karol Gregor (None) · George Papamakarios (University of Edinburgh) · Frederic Besse (DeepMind) · Lars Buesing (DeepMind) · Theophane Weber (DeepMind)

What do you learn from context? Probing for sentence structure in contextualized word representations
Ian Tenney (Google AI Language) · Patrick Xia (Johns Hopkins University) · Berlin Chen (Swarthmore College) · Alex Wang (New York University) · Adam Poliak (Johns Hopkins University) · Tom McCoy (Johns Hopkins University) · Najoung Kim (Johns Hopkins University) · Benjamin Van Durme (Johns Hopkins University) · Samuel R. Bowman (NYU) · Dipanjan Das (Google) · Ellie Pavlick (Brown University)

Learning protein sequence embeddings using information from structure
Tristan Bepler (Massachusetts Institute of Technology) · Bonnie Berger (None)

Learning what and where to attend with humans in the loop
Drew Linsley (Brown University) · Dan Shiebler (Twitter Cortex) · Sven Eberhardt (Amazon) · Thomas Serre (Brown University)

Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
Xue Bin Peng (University of California, Berkeley) · Angjoo Kanazawa (University of California Berkeley) · Samuel Toyer (UC Berkeley) · Pieter Abbeel (UC Berkeley / Embodied Intelligence) · Sergey Levine (UC Berkeley)

How to train your MAML
Antreas Antoniou (University of Edinburgh) · Harrison Edwards (None) · Amos Storkey (None)

Transfer Learning for Sequences via Learning to Collocate
Wanyun Cui (Shanghai University of Finance and Economics) · Guangyu Zheng (Fudan University) · Zhiqiang Shen (Fudan University) · Sihang Jiang (None) · Wei Wang (None)

Learning Implicitly Recurrent CNNs Through Parameter Sharing
Pedro Henrique Pamplona Savarese (Toyota Technological Institute at Chicago) · Michael Maire (University of Chicago)

Learning Actionable Representations with Goal Conditioned Policies
Dibya Ghosh (UC Berkeley) · Abhishek Gupta (UC Berkeley) · Sergey Levine (UC Berkeley)

A Statistical Approach to Assessing Neural Network Robustness
Stefan Webb (University of Oxford) · Tom Rainforth (University of Oxford) · Yee Whye Teh (University of Oxford and DeepMind) · M. Pawan Kumar (University of Oxford)

Random mesh projectors for inverse problems
Konik Kothari (University of Illinois at Urbana Champaign) · Sidharth Gupta (University of Illinois at Urbana-Champaign) · Maarten V de Hoop (Rice University) · Ivan Dokmanic (University of Illinois at Urbana-Champaign)

Adaptive Gradient Methods with Dynamic Bound of Learning Rate
Liangchen Luo (Peking University) · Yuanhao Xiong (Zhejiang University) · Yan Liu (University of Southern California)

Adversarial Attacks on Graph Neural Networks via Meta Learning
Daniel Zügner (Technical University of Munich) · Stephan Günnemann (Technical University of Munich)

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
George Tucker (Google Brain) · Dieterich Lawson (New York University) · Shixiang Gu (University of Cambridge) · Chris J Maddison (University of Toronto)

Pay Less Attention with Lightweight and Dynamic Convolutions
Felix Wu (Cornell University) · Angela Fan (None) · Alexei Baevski (Facebook AI Research) · Yann Dauphin (University of Montreal) · Michael Auli (Facebook AI Research)

Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
Liqian Ma (KU Leuven) · Xu Jia (Huawei Noah's Ark Lab) · Stamatios Georgoulis (ETH Zurich) · Tinne Tuytelaars (KU Leuven) · Luc Gool (None)

Deep Anomaly Detection with Outlier Exposure
Dan Hendrycks (UC Berkeley) · Mantas Mazeika (The University of Chicago) · Thomas Dietterich (Oregon State University)

Stable Recurrent Models
John Miller (UC Berkeley) · Moritz Hardt (None)

Learning Mixed-Curvature Representations in Product Spaces
Albert Gu (Stanford University) · Frederic Sala (Stanford) · Beliz Gunel (Stanford University) · Christopher Re ()

Learning Programmatically Structured Representations with Perceptor Gradients
Svetlin Penkov (The University of Edinburgh) · Subramanian Ramamoorthy (University of Edinburgh)

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Jonathan Frankle (Massachusetts Institute of Technology) · Michael Carbin (MIT)

Learning Exploration Policies for Navigation
Tao Chen (Carnegie Mellon University) · Saurabh Gupta (Facebook AI Research / UIUC) · Abhinav Gupta (None)

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
Wieland Brendel (University of Tuebingen, Germany) · Matthias Bethge (University of Tuebingen)

Three Mechanisms of Weight Decay Regularization
Guodong Zhang (University of Toronto & Vector Institute) · Chaoqi Wang (University of Toronto) · Bowen Xu (None) · Roger Grosse (University of Toronto and Vector Institute)

Theoretical Analysis of Auto Rate-Tuning by Batch Normalization
Sanjeev Arora (Princeton University and Institute for Advanced Study) · Zhiyuan Li (Department of Computer Science, Princeton University) · Kaifeng Lyu (Tsinghua University)

Bayesian Modelling and Monte Carlo Inference for GAN
Hao He (Massachusetts Institute of Technology) · Hao Wang (Massachusetts Institute of Technology) · Guang-He Lee (MIT CSAIL) · Yonglong Tian (MIT)

Overcoming the Disentanglement vs Reconstruction Trade-off via Jacobian Supervision
José Lezama (Universidad de la Republica)

Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural Images
Sanjana Srivastava (Massachusetts Institute of Technology) · Guy Ben-Yosef (MIT) · Xavier Boix (MIT)

Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
Reinhard Heckel (Rice University) · Paul Hand (Northeastern University)

Unsupervised Adversarial Image Reconstruction
Arthur Pajot (Sorbonne Université - LIP6) · Emmanuel de Bézenac (Sorbonne Université) · gallinari patrick (Sorbonne Universite)

Time-Agnostic Prediction: Predicting Predictable Video Frames
Dinesh Jayaraman (UC Berkeley) · Frederik D Ebert (UC Berkeley) · Alexei Efros (UC Berkeley) · Sergey Levine (UC Berkeley)

Transferring Knowledge across Learning Processes
Sebastian Flennerhag (The Alan Turing Institute) · Pablo Moreno (None) · Neil D Lawrence (University of Sheffield and Amazon) · Andreas Damianou (Amazon)

Environment Probing Interaction Policies
Wenxuan Zhou (Carnegie Mellon University) · Lerrel Pinto (School of Computer Science, Carnegie Mellon University) · Abhinav Gupta (None)

Combining Neural Networks with Personalized PageRank for Classification on Graphs
Johannes Klicpera (Technical University Munich) · Aleksandar Bojchevski (Technical University Munich) · Stephan Günnemann (Technical University of Munich)

Generating Multi-Agent Trajectories using Programmatic Weak Supervision
Eric Zhan (California Institute of Technology) · Stephan Zheng (Salesforce) · Yisong Yue (California Institute of Technology) · Long Sha (None) · Patrick Lucey (STATS)

Biologically-Plausible Learning Algorithms Can Scale to Large Datasets
Wu Xiao (Harvard University) · HONGLIN CHEN (University of California, Los Angeles) · Qianli Liao (MIT) · Tomaso Poggio (None)

Dimensionality Reduction for Representing the Knowledge of Probabilistic Models
Marc T Law (University of Toronto and Vector Institute) · Jake Snell (None) · Amir-massoud Farahmand (Vector Institute) · Raquel Urtasun (Department of Computer Science, University of Toronto) · Richard Zemel (Department of Computer Science, University of Toronto)

Defensive Quantization: When Efficiency Meets Robustness
Ji Lin (Tsinghua University) · Chuang Gan (MIT/MIT-IBM Watson AI Lab) · song han (Stanford University)

Neural Logic Machines
Honghua Dong (Tsinghua University) · Jiayuan Mao (MIT CSAIL) · Tian Lin (Google Brain) · Chong Wang (Google) · Lihong Li (Google Inc.) · Dengyong Zhou (None)

Unsupervised Learning of the Set of Local Maxima
Lior Wolf (Facebook AI Research) · Sagie Benaim (Tel Aviv University) · Tomer Galanti (Tel Aviv University)

Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization
Navid Azizan (California Institute of Technology) · Babak Hassibi (None)

DHER: Hindsight Experience Replay for Dynamic Goals
Meng Fang (Tencent) · Cheng Zhou (Hong Kong University of Science and Technology) · Bei Shi (Tencent AI Lab) · Boqing Gong (Tencent AI Lab at Seattle) · Jia Xu (Tencent AI Lab) · Tong Zhang (HKUST)

Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors
Andrew Ilyas (Massachusetts Institute of Technology) · Logan Engstrom (Massachusetts Institute of Technology) · Aleksander Madry (MIT)

Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
Rajarshi Das (Department of Computer Science, University of Massachusetts, Amherst) · Tsendsuren Munkhdalai (UMass) · Eric Yuan (Microsoft Research) · Adam Trischler (Toronto University) · Andrew McCallum (WhizBang Labs)

Meta-learning with differentiable closed-form solvers
Luca Bertinetto (None) · Joao F. Henriques (University of Oxford) · Philip Torr (None) · Andrea Vedaldi (None)

Learning Neural PDE Solvers with Convergence Guarantees
Jun-Ting Hsieh (Stanford University) · Shengjia Zhao (Tsinghua University) · Stephan Eismann (Stanford University) · Lucia Mirabella (Siemens Corporation) · Stefano Ermon (Stanford University)

Harmonic Unpaired Image-to-image Translation
Rui Zhang (Chinese Academic of Sciences) · Tomas Pfister (Google) · Li-Jia Li (None)

BA-Net: Dense Bundle Adjustment Networks
Chengzhou Tang (Simon Fraser University) · Ping Tan (None)

Supervised Community Detection with Line Graph Neural Networks
Zhengdao Chen (New York University) · Xiang Li (Rosebud AI) · Joan Bruna (NYU)

Robustness May Be at Odds with Accuracy
Dimitris Tsipras (MIT) · Shibani Santurkar (MIT) · Logan Engstrom (Massachusetts Institute of Technology) · Alexander Turner (MIT) · Aleksander Madry (MIT)

Variance Reduction for Reinforcement Learning in Input-Driven Environments
Hongzi Mao (The Hong Kong University of Science and Technology) · Shaileshh Bojja Venkatakrishnan (University of Illinois, Urbana Champaign) · Malte Schwarzkopf (MIT CSAIL) · Mohammad Alizadeh (None)

Learning To Solve Circuit-SAT: An Unsupervised Differentiable Approach
Saeed Amizadeh (Microsoft) · Sergiy Matusevych (Microsoft ML.NET) · Markus Weimer (None)

Towards Metamerism via Foveated Style Transfer
Arturo Deza (Harvard) · Aditya Jonnalagadda (None) · Miguel Eckstein (None)

Kernel Change-point Detection with Auxiliary Deep Generative Models
Wei-Cheng Chang (Carnegie Mellon University) · Chun-Liang Li (Machine Learning Department, Carnegie Mellon University) · Yiming Yang (Carnegie Mellon University) · Barnabás Póczos (None)

Mode Normalization
Lucas Deecke (University of Edinburgh) · Iain Murray (University of Edinburgh) · Hakan Bilen (University of Edinburgh)

Predicting the Generalization Gap in Deep Networks with Margin Distributions
YiDing Jiang (Google AI) · Dilip Krishnan (Google) · Hossein Mobahi (Google) · Samy Bengio (Google Brain)

Explaining Image Classifiers by Counterfactual Generation
Chun-Hao Chang (University of Toronto) · Elliot Creager (University of Toronto) · Anna Goldenberg (SickKids/UofT/Vector) · David Duvenaud (University of Toronto)

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
Matthew MacKay (University of Toronto) · Paul Vicol (University of Toronto) · Jonathan Lorraine (University of Toronto) · David Duvenaud (University of Toronto) · Roger Grosse (University of Toronto and Vector Institute)

Unsupervised Control Through Non-Parametric Discriminative Rewards
David Warde-Farley (DeepMind) · Tom Wiele (None) · Tejas Kulkarni (DeepMind) · Catalin Ionescu (Deepmind) · Steven S Hansen (None) · Volodymyr Mnih (None)

Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
Róbert Csordás (IDSIA) · Jürgen Schmidhuber (NNAISENSE, Swiss AI Lab IDSIA (USI & SUPSI))

Subgradient Descent Learns Orthogonal Dictionaries
Yu Bai (Stanford University) · Qijia Jiang (Stanford University) · Ju Sun (Stanford University)

Improving the Generalization of Adversarial Training with Domain Adaptation
Chuanbiao Song (Huazhong University of Science and Technology) · Kun He (Huazhong University of Science and Technology) · Liwei Wang (None) · John E Hopcroft (None)

A Direct Approach to Robust Deep Learning Using Adversarial Networks
huaxia wang (Stevens Institute of Technology) · Chun-Nam Yu (Nokia Bell Labs)

The Implicit Preference Information in an Initial State
Rohin Shah (UC Berkeley) · Dmitrii Krasheninnikov (University of Amsterdam) · Jordan Alexander (Stanford University) · Pieter Abbeel (UC Berkeley / Embodied Intelligence) · Anca Dragan (UC Berkeley)

Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
Junxian He (Carnegie Mellon University) · Daniel Spokoyny (CMU / UCSD) · Graham Neubig (Carnegie Mellon University) · Taylor Berg-Kirkpatrick (University of California, San Diego)

Learning what you can do before doing anything
Oleh Rybkin (University of Pennsylvania) · Karl Pertsch (University of Southern California) · Kosta Derpanis (Ryerson University) · Kostas Daniilidis (University of Pennsylvania) · Andrew Jaegle (University of Pennsylvania)

LanczosNet: Multi-Scale Deep Graph Convolutional Networks
Renjie Liao (University of Toronto) · Zhizhen Zhao (University of Illinois at Urbana-Champaign) · Raquel Urtasun (None) · Richard Zemel (Department of Computer Science, University of Toronto)

Spreading vectors for similarity search
Alexandre Sablayrolles (Facebook) · Matthijs Douze (Facebook) · Cordelia Schmid (Inria/Google) · Hervé Jégou (Facebook AI Research)

Probabilistic Planning with Sequential Monte Carlo methods
Alexandre Piche (Montreal Institute for Learning Algorithms) · Valentin Thomas (University of Montreal) · Cyril Ibrahim (polytechnic Montreal) · Yoshua Bengio (Mila / U. Montreal) · Christopher Pal (Polytechnique Montréal & MILA)

FlowQA: Grasping Flow in History for Conversational Machine Comprehension
Hsin-Yuan Huang (California Institute of Technology) · Eunsol Choi (University of Washington) · Wen-tau Yih (Allen Institute for Artificial Intelligence)

Information asymmetry in KL-regularized RL
Alexandre Galashov (DeepMind) · Siddhant Jayakumar (University of Cambridge) · Leonard Hasenclever (Deepmind) · Dhruva Tirumala Bukkapatnam (DeepMind) · Jonathan Schwarz (DeepMind) · Guillaume Desjardins (University of Montreal) · Wojciech M Czarnecki (Jagiellonian University) · Yee Whye Teh (None) · Razvan Pascanu (DeepMind) · Nicolas Heess (DeepMind)

Diversity-Sensitive Conditional Generative Adversarial Networks
Dingdong Yang (University of Michigan) · Seunghoon Hong (POSTECH) · Yunseok Jang (University of Michigan) · Tianchen Zhao (University of Michigan) · Honglak Lee (Google / U. Michigan)

Fixup Initialization: Residual Learning Without Normalization
Hongyi Zhang (MIT) · Yann Dauphin (University of Montreal) · Tengyu Ma (Facebook)

Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Anirudh Goyal Alias Parth Goyal (MILA, University of Montreal) · Philemon Brakel (University of Montreal) · William Fedus (University of Montreal) · Soumye Singhal (IIT Kanpur) · Timothy Lillicrap (DeepMind & UCL) · Sergey Levine (UC Berkeley) · Hugo Larochelle (Google Brain) · Yoshua Bengio (Mila, University of Montreal)

ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA
Jialin Liu (Unversity of California, Los Angeles (UCLA)) · Xiaohan Chen (Texas A&M University) · Zhangyang Wang (Texas A&M University) · Wotao Yin (University of California, Los Angeles)

Efficient Augmentation via Data Subsampling
Michael Kuchnik (Carnegie Mellon University) · Virginia Smith (Carnegie Mellon University)

Value Propagation Networks
Nantas Nardelli (University of Oxford) · Gabriel Synnaeve (Ecole Normale Supérieure) · Zeming Lin (Facebook AI Research) · Pushmeet Kohli (DeepMind) · Philip Torr (None) · Nicolas Usunier (Facebook AI Research)

Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL
Anusha Nagabandi (UC Berkeley) · Chelsea Finn (University of California Berkeley) · Sergey Levine (UC Berkeley)

Preventing Posterior Collapse with delta-VAEs
Ali Razavi (Deepmind) · Aaron van den Oord (Google Deepmind) · Ben Poole (Google Brain) · Oriol Vinyals (Google DeepMind)

Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-Motion
Ruiqi Gao (University of California, Los Angeles) · Jianwen Xie (Hikvision Research Institute) · Song-Chun Zhu (None) · Yingnian Wu (UCLA)

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Kendall Lowrey (University of Washington) · Aravind Rajeswaran (Indian Institute of Technology Madras) · Sham M Kakade (University of Washington) · Emanuel Todorov (None) · Igor Mordatch (OpenAI)

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Alex Wang (New York University) · Amanpreet Singh (New York University) · Julian Michael (University of Washington) · Felix Hill (DeepMind) · Omer Levy (University of Washington) · Samuel R. Bowman (NYU)

An Empirical Study of Example Forgetting during Deep Neural Network Learning
Mariya Toneva (Carnegie Mellon University) · Alessandro Sordoni (None) · Remi Combes (Massachusetts Institute of Technology) · Adam Trischler (Microsoft Research) · Yoshua Bengio (Mila, University of Montreal) · Geoffrey Gordon (MSR Montreal and CMU MLD)

Optimal Control Via Neural Networks: A Convex Approach
Yize Chen (University of Washington) · Yuanyuan Shi (University of Washington) · Baosen Zhang (Stanford University)

Adaptive Input Representations for Neural Language Modeling
Alexei Baevski (Facebook AI Research) · Michael Auli (Facebook AI Research)

Systematic Generalization: What Is Required and Can It Be Learned?
Dzmitry Bahdanau (Université de Montréal) · Shikhar Murty (University of Montreal) · Mikhail Noukhovitch (Mila (Université de Montréal)) · Thien H Nguyen (University of Oregon) · Harm de Vries (University of Montreal) · Aaron Courville (Mila, U. Montreal)

Automatically Composing Representation Transformations as a Means for Generalization
Michael Chang (University of California, Berkeley) · Abhishek Gupta (UC Berkeley) · Sergey Levine (UC Berkeley) · Thomas L Griffiths (Brown University)

Modeling Uncertainty with Hedged Instance Embeddings
Seong Joon Oh (Clova AI Research) · Andrew Gallagher (None) · Kevin Murphy (None) · Florian Schroff (Google) · Jiyan Pan (Carnegie Mellon University) · Joseph Roth (Google)

Learning to Navigate the Web
Izzeddin Gur (UC Santa Barbara) · Ulrich Rueckert (Google AI) · Aleksandra Faust (Google Brain) · Dilek Hakkani-Tur (Google)

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
Zhiqing Sun (Peking University) · Zhi-Hong Deng (Peking University) · Jian-Yun Nie (None) · Jian Tang (Mila)

STCN: Stochastic Temporal Convolutional Networks
Emre Aksan (ETH Zurich) · Otmar Hilliges (ETH Zurich)

A Closer Look at Few-shot Classification
Wei-Yu Chen (Carnegie Mellon University) · Yen-Cheng Liu (Georgia Tech) · Zsolt Kira (Georgia Tech) · Yu-Chiang Frank Wang (National Taiwan University) · Jia-Bin Huang (Virginia Tech)

A Mean Field Theory of Batch Normalization
Greg Yang (Microsoft Research) · Jeffrey Pennington (Google Brain) · Vinay Rao (Google Brain) · Jascha Sohl-Dickstein (Google Brain) · Samuel S Schoenholz (Google)

TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
Sicong(Sheldon) Huang (Vector Institute, University of Toronto) · Qiyang Li (None) · Cem Anil (None) · Xuchan Bao (None) · Sageev Oore (Google) · Roger Grosse (University of Toronto and Vector Institute)

Visualizing and Understanding Generative Adversarial Networks
David Bau (Massachusetts Institute of Technology) · Jun-Yan Zhu (Massachusetts Institute of Technology) · Hendrik Strobelt (IBM Research, MIT-IBM Watson AI Lab) · Bolei Zhou (None) · Joshua Tenenbaum (None) · William Freeman (None) · Antonio Torralba (None)

Learning to Learn with Conditional Class Dependencies
Xiang Jiang (Imagia and Dalhousie University) · Seyed Mohammad Havaei (Imagia) · Farshid Varno (Dalhousie University) · Gabriel Chartrand (École de technologie supérieure) · Nicolas Chapados (University of Montreal) · Stan Matwin (Dalhousie University)

AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active Tracking
Fangwei Zhong (Peking University) · peng sun (Tencent AI Lab) · Wenhan Luo (Tencent AI Lab) · Tingyun Yan (Tsinghua University) · Yizhou Wang (Peking University)

Feature-Wise Bias Amplification
Klas Leino (Carnegie Mellon University) · Matt Fredrikson (University of Wisconsin, Madison) · Emily Black (Carnegie Mellon University) · Shayak Sen (Carnegie Mellon University) · Anupam Datta (Carnegie Mellon University)

Top-Down Neural Model For Formulae
Karel Chvalovský (Czech Technical University in Prague)

Richard Baraniuk (Rice University) · Jack Wang (Rice University) · Randall Balestriero (RIce University)

Competitive experience replay
Hao Liu (UT Austin) · Alexander Trott (Salesforce) · richard socher (None) · Caiming Xiong (University of California, Los Angeles)

Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
Jonathan Uesato (Massachusetts Institute of Technology) · Ananya Kumar (Stanford University) · Csaba Szepesvari (None) · Tom Erez (DeepMind) · Avraham Ruderman (DeepMind) · Keith Anderson (None) · Krishnamurthy Dvijotham (DeepMind) · Nicolas Heess (DeepMind) · Pushmeet Kohli (DeepMind)

Don't let your Discriminator be fooled
Brady Zhou (Department of Computer Science, University of Texas, Austin) · Philipp Krähenbühl (University of Texas at Austin)

Efficiently testing local optimality and escaping saddles for ReLU networks
Chulhee Yun (MIT) · Suvrit Sra (Massachusetts Institute of Technology) · Ali Jadbabaie (University of Pennsylvania)

Diagnosing and Enhancing VAE Models
Bin Dai (Tsinghua University) · David Wipf (University of California, San Francisco)

Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale Modeling
Josue Nassar (Stony Brook University) · Scott W Linderman (Columbia University) · Monica Bugallo (None) · Il M Park (Stony Brook University)

Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
Yuping Luo (Facebook) · Huazhe Xu (Tsinghua University) · Yuanzhi Li (None) · Yuandong Tian (Google [X], Self-driving car) · Trevor Darrell (UC Berkeley) · Tengyu Ma (Facebook)

Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder
Caio Corro (University of Amsterdam) · Ivan Titov (University of Edinburgh / University of Amsterdam)

Two-Timescale Networks for Nonlinear Value Function Approximation
Wesley Chung (University of Alberta) · Somjit Nath (Jadavpur University, Kolkata) · Ajin Joseph (None) · Martha White (Uni Alberta)

Robustness Certification with Refinement
Gagandeep Singh (Swiss Federal Institute of Technology) · Timon Gehr (None) · Markus Püschel (ETH Zurich) · Martin Vechev (None)

Spherical CNNs on Unstructured Grids
Chiyu Jiang (University of California Berkeley) · Jingwei Huang (Stanford University) · Karthik Kashinath (None) · Mr Prabhat (NERSC) · Philip Marcus (None) · Matthias Niessner (Technical University of Munich)

G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Qi Meng (Microsoft Research Asia) · Shuxin Zheng (University of Science and Technology of China (USTC)) · Huishuai Zhang (Syracuse University) · Wei Chen (None) · Qiwei Ye (Microsoft Research Asia) · Zhi-Ming Ma (None) · Nenghai Yu (None) · Tie-Yan Liu (Microsoft)

Beyond Greedy Ranking: Slate Optimization via List-CVAE
Ray Jiang (DeepMind) · Sven Gowal (DeepMind) · Yuqiu Qian (The University of Hong Kong) · Timothy A Mann (Technion) · Danilo J Rezende (None)

Toward Understanding the Impact of Staleness in Distributed Machine Learning
Wei Dai (School of Computer Science, Carnegie Mellon University) · Yi Zhou (Duke University) · Nanqing Dong (Petuum Inc.;Cornell University) · Hao Zhang (Shanghai Jiao Tong University) · Eric Xing (None)

GANSynth: Adversarial Neural Audio Synthesis
Jesse Engel (Google Brain) · Kumar Agrawal (Google AI) · Shuo Chen (None) · Ishaan Gulrajani (Google) · Chris Donahue (UC San Diego) · Adam Roberts (Google Brain)

Characterizing Audio Adversarial Examples Using Temporal Dependency
Zhuolin Yang (Shanghai Jiao Tong University) · Bo Li (UC Berkeley) · Pin-Yu Chen (IBM Research AI) · Dawn Song (None)

Shoichiro Yamaguchi (Preferred Networks) · Masanori Koyama (None)

Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution
Thomas Elsken (Bosch Center for AI & University of Freiburg) · Jan Metzen (Bosch Center for Artificial Intelligence) · Frank Hutter (University of Freiburg)

On the Sensitivity of Adversarial Robustness to Input Data Distributions
Gavin Ding (Borealis AI) · Yik Chau Lui (Borealis AI) · Xiaomeng Jin (University of Toronto) · Luyu Wang (Borealis AI) · Ruitong Huang (Borealis AI)

Active Learning with Partial Feedback
Peiyun Hu (Carnegie Mellon University) · Zachary Lipton (Carnegie Mellon University) · Anima Anandkumar (Caltech) · Deva Ramanan (School of Computer Science, Carnegie Mellon University)

Guiding Policies with Language via Meta-Learning
John Co-Reyes (University of California Berkeley) · Abhishek Gupta (UC Berkeley) · Suvansh Sanjeev (University of California Berkeley) · Nicholas Altieri (University of California Berkeley) · Jacob Andreas (University of California Berkeley) · John DeNero (None) · Pieter Abbeel (UC Berkeley / Embodied Intelligence) · Sergey Levine (UC Berkeley)

Learnable Embedding Space for Efficient Neural Architecture Compression
Shengcao Cao (Peking University) · Xiaofang Wang (Carnegie Mellon University) · Kris M Kitani (Carnegie Mellon University)

Learning from Incomplete Data with Generative Adversarial Networks
Steven Cheng-Xian Li (University of Massachusetts Amherst) · Bo Jiang (College of Information and Computer Science, University of Massachusetts, Amherst) · Benjamin M Marlin (UMass Amherst)

K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning
Pramod Kaushik Mudrakarta (University of Chicago) · Mark Sandler (Google) · Andrey Zhmoginov (Google) · Andrew Howard (None)

Do Deep Generative Models Know What They Don't Know?
Eric Nalisnick (University of Cambridge) · Akihiro Matsukawa (DeepMind) · Yee Whye Teh (None) · Dilan Gorur (DeepMind) · Balaji Lakshminarayanan (Google DeepMind)

RelGAN: Relational Generative Adversarial Networks for Text Generation
Weili Nie (Rice University) · Nina Narodytska (None) · Ankit B Patel (Rice University, Baylor College of Medicine)

NOODL: Provable Online Dictionary Learning and Sparse Coding
Sirisha Rambhatla (University of Minnesota--Twin Cities) · Xingguo Li (Princeton University) · Jarvis Haupt (University of Minnesota)

Posterior Attention Models for Sequence to Sequence Learning
Shiv Shankar (None) · Sunita Sarawagi (None)

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Michael Janner (UC Berkeley) · Sergey Levine (UC Berkeley) · William Freeman (MIT and Google) · Joshua B Tenenbaum (None) · Chelsea Finn (University of California Berkeley) · Jiajun Wu (MIT)

Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions
Zaiyi Chen (None) · Zhuoning Yuan (University of Iowa) · Jinfeng Yi (JD AI Research) · Bowen Zhou (None) · Enhong Chen (None) · Tianbao Yang (University of Iowa)

SPIGAN: Privileged Adversarial Learning from Simulation
Kuan-Hui Lee (Toyota Research Institute) · German Ros (Intel) · Jie Li (Toyota Research Institute) · Adrien Gaidon (Toyota Research Institute (TRI))

Learning sparse relational transition models
Victoria Xia (Massachusetts Institute of Technology) · Zi Wang (MIT) · Leslie Kaelbling (Massachusetts Institute of Technology)

Multi-Agent Dual Learning
Yiren Wang (University of Illinois at Urbana-Champaign) · Yingce Xia (Microsoft Research Asia) · Tianyu He (University of Science and Technology of China) · Fei Tian (Microsoft Research) · Tao Qin (Microsoft Research Asia) · ChengXiang Zhai (None) · Tie-Yan Liu (Microsoft Research Asia)

Multiple-Attribute Text Rewriting
Guillaume Lample (Facebook) · Sandeep Subramanian (Mila, Universite de Montreal) · Eric Smith (Facebook AI Research) · Ludovic Denoyer (LIP6 - University Pierre et Marie Curie -- Criteo Research) · Marc'Aurelio Ranzato (Facebook AI Research) · Y-Lan Boureau (, New York University)

A Variational Inequality Perspective on Generative Adversarial Networks
Gauthier Gidel (Mila, University of Montreal) · Hugo Berard (None) · Gaëtan Vignoud (Montreal Institute for Learning Algorithms, University of Montreal, University of Montreal) · Pascal Vincent (Facebook AI Research & U.Montreal / MILA) · Simon Lacoste-Julien (MILA, Université de Montréal)

Combinatorial Attacks on Binarized Neural Networks
Elias Khalil (Georgia Institute of Technology) · Amrita Gupta (Georgia Institute of Technology) · Bistra Dilkina (None)

Cost-Sensitive Robustness against Adversarial Examples
XIAO ZHANG (University of Virginia) · David Evans (University of Virginia)

Learning to Design RNA
Frederic Runge (University of Freiburg) · Danny Stoll (None) · Stefan Falkner (None) · Frank Hutter (University of Freiburg)

Learning Procedural Abstractions and Evaluating Discrete Latent Temporal Structure
Karan Goel (Stanford University) · Emma Brunskill (Stanford)

Disjoint Mapping Network for Cross-modal Matching of Voices and Faces
Yandong Wen (Carnegie Mellon Univerisity) · Mahmoud Al Ismail (School of Computer Science, Carnegie Mellon University) · Weiyang Liu (Georgia Institute of Technology) · Bhiksha Raj (Carnegie Mellon University) · Rita Singh (None)

Finite Automata Can be Linearly Decoded from Language-Recognizing RNNs
Joshua J Michalenko (Rice University) · Ameesh Shah (Rice University) · Abhinav Verma (Rice University) · Swarat Chaudhuri (Rice University) · Ankit B Patel (Rice University, Baylor College of Medicine)

Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
Yunzhu Li (MIT) · Jiajun Wu (MIT) · Russ Tedrake (MIT) · Joshua B Tenenbaum (None) · Antonio Torralba (None)

Selfless Sequential Learning
Rahaf Aljundi (KU Leuven) · Marcus Rohrbach (Facebook AI Research) · Tinne Tuytelaars (KU Leuven)

Neural Graph Evolution: Automatic Robot Design
Tingwu Wang (University of Toronto; Vector Institute) · Yuhao Zhou (University of Toronto) · Sanja Fidler () · Jimmy Ba (University of Toronto / Vector Institute)

Contingency-Aware Exploration in Reinforcement Learning
Jongwook Choi (University of Michigan) · Yijie Guo (University of Michigan, Ann Arbor) · Marcin Moczulski (None) · Junhyuk Oh (DeepMind) · Neal Wu (None) · Mohammad Norouzi (Google Brain) · Honglak Lee (Google / U. Michigan)

Interpolation-Prediction Networks for Irregularly Sampled Time Series
Satya Narayan Shukla (University of Massachusetts Amherst) · Benjamin M Marlin (UMass Amherst)

Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks
Patrick CHen (University of California, Los Angeles) · Si Si (Google research) · Sanjiv Kumar (Google Research, NY) · Yang Li (Google) · Cho-Jui Hsieh (UCLA)

Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
Mikael Henaff (Microsoft) · Alfredo Canziani (NYU) · Yann LeCun (None)

Modeling the Long Term Future in Model-Based Reinforcement Learning
Nan Rosemary Ke (MILA, Polytechnique Montreal) · Amanpreet Singh (Facebook AI Research) · Ahmed Touati (MILA) · Anirudh Goyal Alias Parth Goyal (MILA, University of Montreal) · Yoshua Bengio (Mila / U. Montreal) · Devi Parikh (Facebook AI Research / Georgia Tech) · Dhruv Batra (Georgia Tech / Facebook AI Research)

Music Transformer
Anna Huang (Google) · Ashish Vaswani (Google Brain) · Jakob Uszkoreit (Google) · Ian Simon (Google) · Curtis Hawthorne (Google Brain) · Noam Shazeer (Duke University) · Andrew Dai (Google Brain) · Matthew D Hoffman (Adobe) · Monica Dinculescu (Google) · Douglas Eck (Google Brain)

Learning to Infer and Execute 3D Shape Programs
Yonglong Tian (MIT) · Andrew Luo (Massachusetts Institute of Technology) · Xingyuan Sun (Shanghai Jiao Tong University) · Kevin Ellis (None) · William Freeman (MIT and Google) · Joshua B Tenenbaum (None) · Jiajun Wu (MIT)

A Generative Model For Electron Paths
John Bradshaw (University of Cambridge/MPI IS Tuebingen) · Matt Kusner (University of Oxford) · Brooks Paige (University of Oxford) · Marwin Segler (BenevolentAI) · José Miguel Hernández Lobato (University of Cambridge)

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Han Cai (MIT) · Ligeng Zhu (Massachusetts Institute of Technology) · song han (Stanford University)

Revealing interpretable object representations from human behavior
Charles Zheng (National Institute of Mental Health) · Francisco Pereira (Siemens Corporate Research) · Chris I Baker (NIH) · Martin N Hebart (National Institute of Mental Health)

Composing Complex Skills by Learning Transition Policies with Proximity Reward Induction
Youngwoon Lee (University of Southern California) · Shao-Hua Sun (University of Southern California) · Sriram Somasundaram (University of Southern California) · Edward Hu (University of Southern California) · Joseph Lim (University of Southern California)

Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking
Haichuan Yang (University of Rochester) · Yuhao Zhu (University of Rochester) · Ji Liu (University of Rochester; Kwai Inc.)

Stochastic Optimization of Sorting Networks via Continuous Relaxations
Aditya Grover (Stanford University) · Eric Wang (Stanford University) · Aaron Zweig (New York University) · Stefano Ermon (Stanford University)

Learning a Meta-Solver for Syntax-Guided Program Synthesis
Xujie Si (University of Pennsylvania) · Yuan Yang (Georgia Institute of Technology) · Hanjun Dai (Georgia Institute of Technology) · Mayur Naik (University of Pennsylvania) · Le Song (Ant Financial & Georgia Institute of Technology)

Capsule Graph Neural Network
xinyi zhang (Nanyang Technological University) · Lihui Chen (Nanyang Technological University)

Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering
Rajarshi Das (Department of Computer Science, University of Massachusetts, Amherst) · Shehzaad Dhuliawala (Department of Computer Science, University of Massachusetts, Amherst) · Manzil Zaheer (Google) · Andrew McCallum (WhizBang Labs)

Label super-resolution networks
Nikolay Malkin (Yale University) · Caleb Robinson (University of Mississippi) · Le Hou (Stony Brook University) · Rachel Soobitsky (None) · Jacob Czawlytko (None) · Dimitris Samaras (Stony Brook University) · Joel Saltz (None) · Lucas Joppa (None) · Nebojsa Jojic (Microsoft Research)

DyRep: Learning Representations over Dynamic Graphs
Rakshit Trivedi (Georgia Institute of Technology) · Mehrdad Farajtabar (DeepMind) · Prasenjeet Biswal (Georgia Institute of Technology) · Hongyuan Zha (Georgia Institute of Technology)

Predicting the Present and Future States of Multi-agent Systems from Partially-observed Visual Data
Chen Sun (Google) · Per Karlsson (Google) · Jiajun Wu (MIT) · Joshua B Tenenbaum (None) · Kevin Murphy (None)

Synthetic Datasets for Neural Program Synthesis
Richard Shin (UC Berkeley) · Neel Kant (UC Berkeley) · Kavi Gupta (University of California Berkeley) · Christopher Bender (UC Berkeley) · Brandon Trabucco (University of California Berkeley) · Rishabh Singh (Google Brain) · Dawn Song (None)

There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
Ben Athiwaratkun (Cornell University) · Marc A Finzi (Harvey Mudd College) · Pavel Izmailov (Cornell University) · Andrew G Wilson (None)

Towards GAN Benchmarks Which Require Generalization
Ishaan Gulrajani (Google) · Colin Raffel (Google Brain) · Luke Metz (Google Brain)

Eidetic 3D LSTM: A Model for Video Prediction and Beyond
Yunbo Wang (Tsinghua University) · Lu Jiang (Google AI) · Ming-Hsuan Yang (University of California at Merced) · Li-Jia Li (None) · Mingsheng Long (Tsinghua University) · Li Fei-Fei (Stanford University)

Poincare Glove: Hyperbolic Word Embeddings
Alexandru Tifrea (ETH Zurich) · Gary Bécigneul (ETH Zürich & MPI Tübingen) · Octavian Ganea (Swiss Federal Institute of Technology)

On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks
Yukun Ding (University of Notre Dame) · Jinglan Liu (University of Notre Dame) · Jinjun Xiong (IBM T.J. Watson Research Center) · Yiyu Shi (None)

A generative adversarial network for style modeling in a text-to-speech system
shuang ma (University of New York at Buffalo) · Daniel McDuff (Microsoft Research & AI) · Yale Song (Microsoft)

Rethinking the Value of Network Pruning
Zhuang Liu (UC Berkeley) · Mingjie Sun (Tsinghua University) · Tinghui Zhou (None) · Gao Huang (Cornell University) · Trevor Darrell (UC Berkeley)

Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
Chien-Sheng Wu (The Hong Kong University of Science and Technology) · richard socher (None) · Caiming Xiong (University of California, Los Angeles)

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference
Matt Riemer (IBM Research AI) · Juan Ignacio Cases Martin (Stanford University) · Robert Ajemian (Massachusetts Institute of Technology) · Miao Liu (IBM) · Irina Rish (IBM Research AI) · Yuhai Tu (None) · Gerald Tesauro (IBM Research)

The Limitations of Adversarial Training and the Blind-Spot Attack
Huan Zhang (UCLA) · Hongge Chen (MIT) · Zhao Song (None) · Duane S Boning (MIT) · Inderjit S Dhillon (None) · Cho-Jui Hsieh (UCLA)

Towards Robust, Locally Linear Deep Networks
Guang-He Lee (MIT) · David Alvarez-Melis (None) · Tommi Jaakkola (MIT)

Regularized Learning for Domain Adaptation under Label Shifts
Kamyar Azizzadenesheli (UCI-Caltech) · Anqi Liu (Caltech) · Fanny Yang (Stanford University, ETH Zurich) · Anima Anandkumar (Caltech)