ICLR 2020

687 papers

Continual learning with hypernetworks

Johannes von Oswald, Christian Henning, Benjamin F. Grewe, João Sacramento

Phase Transitions for the Information Bottleneck in Representation Learning

Tailin Wu, Ian Fischer

Variational Template Machine for Data-to-Text Generation

Rong Ye, Wenxian Shi, Hao Zhou, zhongyu wei, Lei Li

Memory-Based Graph Networks

Amir Hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris

Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)

Peter Sorrenson, Carsten Rother, Ullrich Köthe

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Dan Hendrycks*, Norman Mu*, Ekin Dogus Cubuk, Barret Zoph, Justin Gilmer

AtomNAS: Fine-Grained End-to-End Neural Architecture Search

Jieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin, Linjie Yang

Residual Energy-Based Models for Text Generation

Yuntian Deng, Anton Bakhtin, Myle Ott, arthur szlam, Marc'aurelio Ranzato

Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps

Tri Dao, Nimit Sohoni, Albert Gu, Matthew Eichhorn, Amit Blonder

A closer look at the approximation capabilities of neural networks

Kai Fong Ernest Chong

Improving Generalization in Meta Reinforcement Learning using Learned Objectives

Louis Kirsch, Sjoerd van Steenkiste, Juergen Schmidhuber

Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks

Haoran You, Chaojian Li, Pengfei Xu, Yonggan Fu, Yue Wang

Deep Audio Priors Emerge From Harmonic Convolutional Networks

Zhoutong Zhang, Yunyun Wang, Chuang Gan, Jiajun Wu, Joshua B. Tenenbaum

Truth or backpropaganda? An empirical investigation of deep learning theory

Micah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein

Expected Information Maximization: Using the I-Projection for Mixture Density Estimation

Philipp Becker, Oleg Arenz, Gerhard Neumann

A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms

Yoshua Bengio, Tristan Deleu, Nasim Rahaman, Nan Rosemary Ke, Sébastien Lachapelle

On the interaction between supervision and self-play in emergent communication

Ryan Lowe*, Abhinav Gupta*, Jakob Foerster, Douwe Kiela, Joelle Pineau

Dynamic Model Pruning with Feedback

Tao LIN, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi

Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings

Shweta Mahajan, Iryna Gurevych, Stefan Roth

Transferring Optimality Across Data Distributions via Homotopy Methods

Matilde Gargiani, Andrea Zanelli, Quoc Tran Dinh, Moritz Diehl, Frank Hutter

Gradient Descent Maximizes the Margin of Homogeneous Neural Networks

Kaifeng Lyu, Jian Li

Regularizing activations in neural networks via distribution matching with the Wasserstein metric

Taejong Joo, Donggu Kang, Byunghoon Kim

Mutual Information Gradient Estimation for Representation Learning

Liangjian Wen, Yiji Zhou, LIRONG HE, Mingyuan Zhou, Zenglin Xu

Lite Transformer with Long-Short Range Attention

Zhanghao Wu*, Zhijian Liu*, Ji Lin, Yujun Lin, Song Han

A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case

Greg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro

Adversarial Training and Provable Defenses: Bridging the Gap

Mislav Balunovic, Martin Vechev

Adversarial Lipschitz Regularization

Dávid Terjék

Compositional Language Continual Learning

Yuanpeng Li, Liang Zhao, Kenneth Church, Mohamed Elhoseiny

End to End Trainable Active Contours via Differentiable Rendering

Shir Gur, Tal Shaharabany, Lior Wolf

Provable Filter Pruning for Efficient Neural Networks

Lucas Liebenwein, Cenk Baykal, Harry Lang, Dan Feldman, Daniela Rus

Effect of Activation Functions on the Training of Overparametrized Neural Nets

Abhishek Panigrahi, Abhishek Shetty, Navin Goyal

Lipschitz constant estimation of Neural Networks via sparse polynomial optimization

Fabian Latorre, Paul Rolland, Volkan Cevher

Neural Arithmetic Units

Andreas Madsen, Alexander Rosenberg Johansen

State Alignment-based Imitation Learning

Fangchen Liu, Zhan Ling, Tongzhou Mu, Hao Su

Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories

Tiange Luo, Kaichun Mo, Zhiao Huang, Jiarui Xu, Siyu Hu

Discriminative Particle Filter Reinforcement Learning for Complex Partial observations

Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee, Nan Ye

Unrestricted Adversarial Examples via Semantic Manipulation

Anand Bhattad, Min Jin Chong, Kaizhao Liang, Bo Li, D. A. Forsyth

Classification-Based Anomaly Detection for General Data

Liron Bergman, Yedid Hoshen

DeepSphere: a graph-based spherical CNN

Michaël Defferrard, Martino Milani, Frédérick Gusset, Nathanael Perraudin

Scale-Equivariant Steerable Networks

Ivan Sosnovik, Michał Szmaja, Arnold Smeulders

SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models

Yucen Luo, Alex Beatson, Mohammad Norouzi, Jun Zhu, David Duvenaud

On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning

Jian Li, Xuanyuan Luo, Mingda Qiao

Consistency Regularization for Generative Adversarial Networks

Han Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee

Differentiable learning of numerical rules in knowledge graphs

Po-Wei Wang, Daria Stepanova, Csaba Domokos, J. Zico Kolter

Deep Learning For Symbolic Mathematics

Guillaume Lample, Francois Charton

Learning to Move with Affordance Maps

William Qi, Ravi Teja Mullapudi, Saurabh Gupta, Deva Ramanan

Neural tangent kernels, transportation mappings, and universal approximation

Ziwei Ji, Matus Telgarsky, Ruicheng Xian

SCALOR: Generative World Models with Scalable Object Representations

Jindong Jiang*, Sepehr Janghorbani*, Gerard de Melo, Sungjin Ahn

Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks

Tribhuvanesh Orekondy, Bernt Schiele, Mario Fritz

Making Sense of Reinforcement Learning and Probabilistic Inference

Brendan O'Donoghue, Ian Osband, Catalin Ionescu

Differentiable Reasoning over a Virtual Knowledge Base

Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov

Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent Variable Models

Yixuan Qiu, Lingsong Zhang, Xiao Wang

Domain Adaptive Multibranch Networks

Róger Bermúdez-Chacón, Mathieu Salzmann, Pascal Fua

A Mutual Information Maximization Perspective of Language Representation Learning

Lingpeng Kong, Cyprien de Masson d'Autume, Lei Yu, Wang Ling, Zihang Dai

DiffTaichi: Differentiable Programming for Physical Simulation

Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr

Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning

Arsenii Ashukha, Alexander Lyzhov, Dmitry Molchanov, Dmitry Vetrov

Federated Learning with Matched Averaging

Hongyi Wang, Mikhail Yurochkin, Yuekai Sun, Dimitris Papailiopoulos, Yasaman Khazaeni

Energy-based models for atomic-resolution protein conformations

Yilun Du, Joshua Meier, Jerry Ma, Rob Fergus, Alexander Rives

Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem

Vaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang

Episodic Reinforcement Learning with Associative Memory

Guangxiang Zhu*, Zichuan Lin*, Guangwen Yang, Chongjie Zhang

Sub-policy Adaptation for Hierarchical Reinforcement Learning

Alexander Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel

Critical initialisation in continuous approximations of binary neural networks

George Stamatescu, Federica Gerace, Carlo Lucibello, Ian Fuss, Langford White

Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint

Jimmy Ba, Murat Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang

Reconstructing continuous distributions of 3D protein structure from cryo-EM images

Ellen D. Zhong, Tristan Bepler, Joseph H. Davis, Bonnie Berger

Deep Orientation Uncertainty Learning based on a Bingham Loss

Igor Gilitschenski, Roshni Sahoo, Wilko Schwarting, Alexander Amini, Sertac Karaman

Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring in Data

David W. Romero, Mark Hoogendoorn

PROGRESSIVE LEARNING AND DISENTANGLEMENT OF HIERARCHICAL REPRESENTATIONS

Zhiyuan Li, Jaideep Vitthal Murkute, Prashnna Kumar Gyawali, Linwei Wang

Mixed Precision DNNs: All you need is a good parametrization

Stefan Uhlich, Lukas Mauch, Fabien Cardinaux, Kazuki Yoshiyama, Javier Alonso Garcia

Information Geometry of Orthogonal Initializations and Training

Piotr Aleksander Sokół, Il Memming Park

Extreme Classification via Adversarial Softmax Approximation

Robert Bamler, Stephan Mandt

Learning Nearly Decomposable Value Functions Via Communication Minimization

Tonghan Wang*, Jianhao Wang*, Chongyi Zheng, Chongjie Zhang

Robust Subspace Recovery Layer for Unsupervised Anomaly Detection

Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman

Learning to Coordinate Manipulation Skills via Skill Behavior Diversification

Youngwoon Lee, Jingyun Yang, Joseph J. Lim

NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search

Arber Zela, Julien Siems, Frank Hutter

Conservative Uncertainty Estimation By Fitting Prior Networks

Kamil Ciosek, Vincent Fortuin, Ryota Tomioka, Katja Hofmann, Richard Turner

Understanding Generalization in Recurrent Neural Networks

Zhuozhuo Tu, Fengxiang He, Dacheng Tao

The Shape of Data: Intrinsic Distance for Data Distributions

Anton Tsitsulin, Marina Munkhoeva, Davide Mottin, Panagiotis Karras, Alex Bronstein

How to 0wn the NAS in Your Spare Time

Sanghyun Hong, Michael Davinroy, Yigitcan Kaya, Dana Dachman-Soled, Tudor Dumitras

Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation

Nitin Rathi, Gopalakrishnan Srinivasan, Priyadarshini Panda, Kaushik Roy

An Exponential Learning Rate Schedule for Deep Learning

Zhiyuan Li, Sanjeev Arora

BREAKING CERTIFIED DEFENSES: SEMANTIC ADVERSARIAL EXAMPLES WITH SPOOFED ROBUSTNESS CERTIFICATES

Amin Ghiasi, Ali Shafahi, Tom Goldstein

Query-efficient Meta Attack to Deep Neural Networks

JIAWEI DU, Hu Zhang, Joey Tianyi Zhou, Yi Yang, Jiashi Feng

Massively Multilingual Sparse Word Representations

Gábor Berend

Monotonic Multihead Attention

Xutai Ma, Juan Miguel Pino, James Cross, Liezl Puzon, Jiatao Gu

Gradients as Features for Deep Representation Learning

Fangzhou Mu, Yingyu Liang, Yin Li

Geom-GCN: Geometric Graph Convolutional Networks

Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang

Pay Attention to Features, Transfer Learn Faster CNNs

Kafeng Wang, Xitong Gao, Yiren Zhao, Xingjian Li, Dejing Dou