ICLR 2020

687 papers

Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations

Yichi Zhang, Ritchie Zhao, Weizhe Hua, Nayun Xu, G. Edward Suh

Oblique Decision Trees from Derivatives of ReLU Networks

Guang-He Lee, Tommi S. Jaakkola

Span Recovery for Deep Neural Networks with Applications to Input Obfuscation

Rajesh Jayaram, David P. Woodruff, Qiuyi Zhang

Improving Neural Language Generation with Spectrum Control

Lingxiao Wang, Jing Huang, Kevin Huang, Ziniu Hu, Guangtao Wang

Learn to Explain Efficiently via Neural Logic Inductive Learning

Yuan Yang, Le Song

Improved memory in recurrent neural networks with sequential non-normal dynamics

Emin Orhan, Xaq Pitkow

Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees

Binghong Chen, Bo Dai, Qinjie Lin, Guo Ye, Han Liu

Neural Module Networks for Reasoning over Text

Nitish Gupta, Kevin Lin, Dan Roth, Sameer Singh, Matt Gardner

Higher-Order Function Networks for Learning Composable 3D Object Representations

Eric Mitchell, Selim Engin, Volkan Isler, Daniel D Lee

Symplectic Recurrent Neural Networks

Zhengdao Chen, Jianyu Zhang, Martin Arjovsky, Léon Bottou

Asymptotics of Wide Networks from Feynman Diagrams

Ethan Dyer, Guy Gur-Ari

Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling

Hao Zhang, Bo Chen, Long Tian, Zhengjue Wang, Mingyuan Zhou

Towards Fast Adaptation of Neural Architectures with Meta Learning

Dongze Lian, Yin Zheng, Yintao Xu, Yanxiong Lu, Leyu Lin

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

Prithviraj Ammanabrolu, Matthew Hausknecht

GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding

Chenhui Deng, Zhiqiang Zhao, Yongyu Wang, Zhiru Zhang, Zhuo Feng

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control

Nir Levine, Yinlam Chow, Rui Shu, Ang Li, Mohammad Ghavamzadeh

Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History

Yiheng Zhou, Yulia Tsvetkov, Alan W Black, Zhou Yu

BERTScore: Evaluating Text Generation with BERT

Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, Yoav Artzi

Neural Execution of Graph Algorithms

Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell

On the Need for Topology-Aware Generative Models for Manifold-Based Defenses

Uyeong Jang, Susmit Jha, Somesh Jha

FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary

Yingzhen Yang, Jiahui Yu, Nebojsa Jojic, Jun Huan, Thomas S. Huang

Capsules with Inverted Dot-Product Attention Routing

Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov

Composition-based Multi-Relational Graph Convolutional Networks

Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha Talukdar

Gradient-Based Neural DAG Learning

Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu, Simon Lacoste-Julien

The Local Elasticity of Neural Networks

Hangfeng He, Weijie Su

Composing Task-Agnostic Policies with Deep Reinforcement Learning

Ahmed H. Qureshi, Jacob J. Johnson, Yuzhe Qin, Taylor Henderson, Byron Boots

Convergence of Gradient Methods on Bilinear Zero-Sum Games

Guojun Zhang, Yaoliang Yu

Discovering Motor Programs by Recomposing Demonstrations

Tanmay Shankar, Shubham Tulsiani, Lerrel Pinto, Abhinav Gupta

Learning from Explanations with Neural Execution Tree

Ziqi Wang*, Yujia Qin*, Wenxuan Zhou, Jun Yan, Qinyuan Ye

Jelly Bean World: A Testbed for Never-Ending Learning

Emmanouil Antonios Platanios, Abulhair Saparov, Tom Mitchell

Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization

Satrajit Chatterjee

Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural Networks

Xin Xing, Long Sha, Pengyu Hong, Zuofeng Shang, Jun S. Liu

MEMO: A Deep Network for Flexible Combination of Episodic Memories

Andrea Banino, Adrià Puigdomènech Badia, Raphael Koster, Martin J. Chadwick, Vinicius Zambaldi

Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality

Saurabh Khanna, Vincent Y. F. Tan

Harnessing Structures for Value-Based Planning and Reinforcement Learning

Yuzhe Yang, Guo Zhang, Zhi Xu, Dina Katabi

Bayesian Meta Sampling for Fast Uncertainty Adaptation

Zhenyi Wang, Yang Zhao, Ping Yu, Ruiyi Zhang, Changyou Chen

Non-Autoregressive Dialog State Tracking

Hung Le, Richard Socher, Steven C.H. Hoi

Extreme Tensoring for Low-Memory Preconditioning

Xinyi Chen, Naman Agarwal, Elad Hazan, Cyril Zhang, Yi Zhang

RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?

Anil Kag, Ziming Zhang, Venkatesh Saligrama

The Early Phase of Neural Network Training

Jonathan Frankle, David J. Schwab, Ari S. Morcos

Learning The Difference That Makes A Difference With Counterfactually-Augmented Data

Divyansh Kaushik, Eduard Hovy, Zachary Lipton

NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension

Seohyun Back, Sai Chetan Chinthakindi, Akhil Kedia, Haejun Lee, Jaegul Choo

Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization

Junjie Yan, Ruosi Wan, Xiangyu Zhang, Wei Zhang, Yichen Wei

Single Episode Policy Transfer in Reinforcement Learning

Jiachen Yang, Brenden Petersen, Hongyuan Zha, Daniel faissol

Comparing Rewinding and Fine-tuning in Neural Network Pruning

Alex Renda, Jonathan Frankle, Michael Carbin

Generalization through Memorization: Nearest Neighbor Language Models

Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, Mike Lewis

Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention

Chen Zhao, Chenyan Xiong, Corby Rosset, XIA SONG, Paul Bennett

Synthesizing Programmatic Policies that Inductively Generalize

Jeevana Priya Inala, Osbert Bastani, Zenna Tavares, Armando Solar-Lezama

Decoding As Dynamic Programming For Recurrent Autoregressive Models

Najam Zaidi, Trevor Cohn, Gholamreza Haffari

Deep Double Descent: Where Bigger Models and More Data Hurt

Preetum Nakkiran, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak

Intriguing Properties of Adversarial Training at Scale

Cihang Xie, Alan Yuille

Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks

Leopold Cambier, Anahita Bhiwandiwalla, Ting Gong, Oguz H. Elibol, Mehran Nekuii

Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?

Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang

Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication

Yuanhao Wang, Jiachen Hu, Xiaoyu Chen, Liwei Wang

Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networks

Timothy Tadros, Giri Krishnan, Ramyaa Ramyaa, Maxim Bazhenov

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

Hengyuan Hu, Jakob N Foerster

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks

Hugo Berard, Gauthier Gidel, Amjad Almahairi, Pascal Vincent, Simon Lacoste-Julien

On the Global Convergence of Training Deep Linear ResNets

Difan Zou, Philip M. Long, Quanquan Gu

Towards a Deep Network Architecture for Structured Smoothness

Haroun Habeeb, Oluwasanmi Koyejo

Meta-Q-Learning

Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola

Revisiting Self-Training for Neural Sequence Generation

Junxian He, Jiatao Gu, Jiajun Shen, Marc'aurelio Ranzato

Network Deconvolution

Chengxi Ye, Matthew Evanusa, Hua He, Anton Mitrokhin, Tom Goldstein

Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators

Reinhard Heckel and Mahdi Soltanolkotabi

Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities

Baichuan Yuan, Xiaowei Wang, Jianxin Ma, Chang Zhou, Andrea L. Bertozzi

Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension

Xinyun Chen, Chen Liang, Adams Wei Yu, Denny Zhou, Dawn Song

Model-Augmented Actor-Critic: Backpropagating through Paths

Ignasi Clavera, Yao Fu, Pieter Abbeel

LambdaNet: Probabilistic Type Inference using Graph Neural Networks

Jiayi Wei, Maruth Goyal, Greg Durrett, Isil Dillig

Real or Not Real, that is the Question

Yuanbo Xiangli*, Yubin Deng*, Bo Dai*, Chen Change Loy, Dahua Lin

From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech

Hyeong-Seok Choi, Changdae Park, Kyogu Lee

Dream to Control: Learning Behaviors by Latent Imagination

Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi

Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping

Adam W. Harley, Shrinidhi K. Lakshmikanth, Fangyu Li, Xian Zhou, Hsiao-Yu Fish Tung

Decoupling Representation and Classifier for Long-Tailed Recognition

Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo

Robust Reinforcement Learning for Continuous Control with Model Misspecification

Daniel J. Mankowitz, Nir Levine, Rae Jeong, Abbas Abdolmaleki, Jost Tobias Springenberg

Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework

Zirui Wang*, Jiateng Xie*, Ruochen Xu, Yiming Yang, Graham Neubig

Training Recurrent Neural Networks Online by Learning Explicit State Variables

Somjit Nath, Vincent Liu, Alan Chan, Xin Li, Adam White

Uncertainty-guided Continual Learning with Bayesian Neural Networks

Sayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell, Marcus Rohrbach

Curriculum Loss: Robust Learning and Generalization against Label Corruption

Yueming LYU, Ivor W. Tsang

Picking Winning Tickets Before Training by Preserving Gradient Flow

Chaoqi Wang, Guodong Zhang, Roger Grosse

Generative Models for Effective ML on Private, Decentralized Datasets

Sean Augenstein, H. Brendan McMahan, Daniel Ramage, Swaroop Ramaswamy, Peter Kairouz

A Probabilistic Formulation of Unsupervised Text Style Transfer

Junxian He, Xinyi Wang, Graham Neubig, Taylor Berg-Kirkpatrick

Inductive representation learning on temporal graphs

Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning

Yeming Wen, Dustin Tran, Jimmy Ba

Towards neural networks that provably know when they don't know

Alexander Meinke, Matthias Hein

Iterative energy-based projection on a normal data manifold for anomaly localization

David Dehaene, Oriel Frigo, Sébastien Combrexelle, Pierre Eline

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal, Robert Stanforth

Frequency-based Search-control in Dyna

Yangchen Pan, Jincheng Mei, Amir-massoud Farahmand

Mathematical Reasoning in Latent Space

Dennis Lee, Christian Szegedy, Markus Rabe, Sarah Loos, Kshitij Bansal

Learning representations for binary-classification without backpropagation

Mathias Lechner

Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks

Ziwei Ji, Matus Telgarsky

Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics

Sungyong Seo*, Chuizheng Meng*, Yan Liu

HiLLoC: lossless image compression with hierarchical latent variable models

James Townsend, Thomas Bird, Julius Kunze, David Barber

IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks

Michael Luo, Jiahao Yao, Richard Liaw, Eric Liang, Ion Stoica

A Theory of Usable Information under Computational Constraints

Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon

On Bonus Based Exploration Methods In The Arcade Learning Environment

Adrien Ali Taiga, William Fedus, Marlos C. Machado, Aaron Courville, Marc G. Bellemare

Xinjie Fan, Yizhe Zhang, Zhendong Wang, Mingyuan Zhou

Smoothness and Stability in GANs

Casey Chu, Kentaro Minami, Kenji Fukumizu

SNOW: Subscribing to Knowledge via Channel Pooling for Transfer & Lifelong Learning of Convolutional Neural Networks

Chungkuk Yoo, Bumsoo Kang, Minsik Cho

Empirical Studies on the Properties of Linear Regions in Deep Neural Networks

Xiao Zhang, Dongrui Wu

Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning

Ali Mousavi, Lihong Li, Qiang Liu, Denny Zhou

PairNorm: Tackling Oversmoothing in GNNs

Lingxiao Zhao, Leman Akoglu