ICLR 2018

337 papers

Demystifying MMD GANs

Mikołaj Bińkowski, Danica J. Sutherland, Michael Arbel, Arthur Gretton

Communication Algorithms via Deep Learning

Hyeji Kim, Yihan Jiang, Ranvir B. Rana, Sreeram Kannan, Sewoong Oh

Deep Rewiring: Training very sparse deep networks

Guillaume Bellec, David Kappel, Wolfgang Maass, Robert Legenstein

All-but-the-Top: Simple and Effective Postprocessing for Word Representations

Jiaqi Mu, Pramod Viswanath

DCN+: Mixed Objective And Deep Residual Coattention for Question Answering

Caiming Xiong, Victor Zhong, Richard Socher

Ensemble Adversarial Training: Attacks and Defenses

Florian Tramer, Alexey Kurakin, Nicolas Papernot, Ian Goodfellow, Dan Boneh

PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples

Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman

META LEARNING SHARED HIERARCHIES

Kevin Frans, Jonathan Ho, Xi Chen, Pieter Abbeel, John Schulman

Deep Neural Networks as Gaussian Processes

Jaehoon Lee, Yasaman Bahri, Roman Novak, Samuel S. Schoenholz, Jeffrey Pennington

Policy Optimization by Genetic Distillation

Tanmay Gangwani, Jian Peng

Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent

Zhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng, Alexander Miller

Boosting the Actor with Dual Critic

Bo Dai, Albert Shaw, Niao He, Lihong Li, Le Song

Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning

Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar

Towards Reverse-Engineering Black-Box Neural Networks

Seong Joon Oh, Max Augustin, Mario Fritz, Bernt Schiele

Debiasing Evidence Approximations: On Importance-weighted Autoencoders and Jackknife Variational Inference

Sebastian Nowozin

Breaking the Softmax Bottleneck: A High-Rank RNN Language Model

Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov, William W. Cohen

Distributed Distributional Deterministic Policy Gradients

Gabriel Barth-Maron, Matthew W. Hoffman, David Budden, Will Dabney, Dan Horgan

Residual Loss Prediction: Reinforcement Learning With No Incremental Feedback

Hal Daume III, John Langford, Amr Sharaf

Kernel Implicit Variational Inference

Jiaxin Shi, Shengyang Sun, Jun Zhu

Synthesizing realistic neural population activity patterns using Generative Adversarial Networks

Manuel Molano-Mazon, Arno Onken, Eugenio Piasini*, Stefano Panzeri*

Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples

Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin

On the Convergence of Adam and Beyond

Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

Quantitatively Evaluating GANs With Divergences Proposed for Training

Daniel Jiwoong Im, He Ma, Graham W. Taylor, Kristin Branson

Learning Wasserstein Embeddings

Nicolas Courty, Rémi Flamary, Melanie Ducoffe

Unbiased Online Recurrent Optimization

Corentin Tallec, Yann Ollivier

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis

Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli

Deep Learning as a Mixed Convex-Combinatorial Optimization Problem

Abram L. Friesen, Pedro Domingos

A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro

A Scalable Laplace Approximation for Neural Networks

Hippolyt Ritter, Aleksandar Botev, David Barber

Understanding Short-Horizon Bias in Stochastic Meta-Optimization

Yuhuai Wu, Mengye Ren, Renjie Liao, Roger Grosse.

Learning From Noisy Singly-labeled Data

Ashish Khetan, Zachary C. Lipton, Animashree Anandkumar

Learning One-hidden-layer Neural Networks with Landscape Design

Rong Ge, Jason D. Lee, Tengyu Ma

Do GANs learn the distribution? Some Theory and Empirics

Sanjeev Arora, Andrej Risteski, Yi Zhang

Towards Synthesizing Complex Programs From Input-Output Examples

Xinyun Chen, Chang Liu, Dawn Song

The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning

Audrunas Gruslys, Will Dabney, Mohammad Gheshlaghi azar, Bilal Piot, Marc Bellemare

On the Discrimination-Generalization Tradeoff in GANs

Pengchuan Zhang, Qiang Liu, Dengyong Zhou, Tao Xu, Xiaodong He

WRPN: Wide Reduced-Precision Networks

Asit Mishra, Eriko Nurvitadhi, Jeffrey J Cook, Debbie Marr

Learning how to explain neural networks: PatternNet and PatternAttribution

Pieter-jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan

The Kanerva Machine: A Generative Distributed Memory

Yan Wu, Greg Wayne, Alex Graves, Timothy Lillicrap

Attacking Binarized Neural Networks

Angus Galloway, Graham W. Taylor, Medhat Moussa

Emergent Communication in a Multi-Modal, Multi-Step Referential Game

Katrina Evtimova, Andrew Drozdov, Douwe Kiela, Kyunghyun Cho

Monotonic Chunkwise Attention

Chung-Cheng Chiu*, Colin Raffel*

Learning Awareness Models

Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo

Latent Space Oddity: on the Curvature of Deep Generative Models

Georgios Arvanitidis, Lars Kai Hansen, Søren Hauberg

Training GANs with Optimism

Constantinos Daskalakis, Andrew Ilyas, Vasilis Syrgkanis, Haoyang Zeng

Implicit Causal Models for Genome-wide Association Studies

Dustin Tran, David M. Blei

Adaptive Dropout with Rademacher Complexity Regularization

Ke Zhai, Huan Wang

Neural Language Modeling by Jointly Learning Syntax and Lexicon

Yikang Shen, Zhouhan Lin, Chin-Wei Huang, Aaron Courville

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning

Benjamin Eysenbach, Shixiang Gu, Julian Ibarz, Sergey Levine

NerveNet: Learning Structured Policy with Graph Neural Networks

Tingwu Wang, Renjie Liao, Jimmy Ba, Sanja Fidler

Unsupervised Machine Translation Using Monolingual Corpora Only

Guillaume Lample, Alexis CONNEAU, Ludovic DENOYER, Marc'aurelio Ranzato

Towards better understanding of gradient-based attribution methods for Deep Neural Networks

Marco Ancona, Enea Ceolini, Cengiz Oztireli, Markus Gross

Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering

Elliot Meyerson, Risto Miikkulainen

Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings

Kangwook Lee, Hoon Kim, Changho Suh

SEARNN: Training RNNs with global-local losses

Rémi Leblond, Jean-Baptiste Alayrac, Anton Osokin, Simon Lacoste-Julien

Stabilizing Adversarial Nets with Prediction Methods

Abhay Yadav, Sohil Shah, Zheng Xu, David Jacobs, Tom Goldstein

Large Scale Optimal Transport and Mapping Estimation

Vivien Seguy, Bharath Bhushan Damodaran, Rémi Flamary, Nicolas Courty, Antoine Rolet

Generating Natural Adversarial Examples

Zhengli Zhao, Dheeru Dua, Sameer Singh

Consequentialist conditional cooperation in social dilemmas with imperfect information

Alexander Peysakhovich, Adam Lerer

Can recurrent neural networks warp time?

Corentin Tallec, Yann Ollivier

Dynamic Neural Program Embeddings for Program Repair

Ke Wang, Rishabh Singh, Zhendong Su

Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks

Víctor Campos, Brendan Jou, Xavier Giró-i-Nieto, Jordi Torres, Shih-fu Chang

Multi-Mention Learning for Reading Comprehension with Neural Cascades

Swabha Swayamdipta, Ankur P. Parikh, Tom Kwiatkowski

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

William Fedus*, Mihaela Rosca*, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed

A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs

Sanjeev Arora, Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli

Deep Active Learning for Named Entity Recognition

Yanyao Shen, Hyokun Yun, Zachary C. Lipton, Yakov Kronrod, Animashree Anandkumar

Variational image compression with a scale hyperprior

Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston

Hierarchical Subtask Discovery with Non-Negative Matrix Factorization

Adam C. Earle, Andrew M. Saxe, Benjamin Rosman

Generalizing Across Domains via Cross-Gradient Training

Shiv Shankar*, Vihari Piratla*, Soumen Chakrabarti, Siddhartha Chaudhuri, Preethi Jyothi

Compositional Attention Networks for Machine Reasoning

Drew A. Hudson, Christopher D. Manning

Parameter Space Noise for Exploration

Matthias Plappert, Rein Houthooft, Prafulla Dhariwal, Szymon Sidor, Richard Y. Chen

Zero-Shot Visual Imitation

Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo, Pulkit Agrawal, Dian Chen

A DIRT-T Approach to Unsupervised Domain Adaptation

Rui Shu, Hung Bui, Hirokazu Narui, Stefano Ermon

Empirical Risk Landscape Analysis for Understanding Deep Neural Networks

Pan Zhou, Jiashi Feng

Learning Intrinsic Sparse Structures within Long Short-Term Memory

Wei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang, Wenhan Wang

Learning Deep Mean Field Games for Modeling Large Population Behavior

Jiachen Yang, Xiaojing Ye, Rakshit Trivedi, Huan Xu, Hongyuan Zha

Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions

Sjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber

Mixed Precision Training

Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen

Towards Image Understanding from Deep Compression Without Decoding

Robert Torfason, Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte

Twin Networks: Matching the Future for Sequence Generation

Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Adam Trischler, Chris Pal

Residual Connections Encourage Iterative Inference

Stanisław Jastrzebski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che

Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy

Asit Mishra, Debbie Marr

A Hierarchical Model for Device Placement

Azalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc V. Le

Matrix capsules with EM routing

Geoffrey E Hinton, Sara Sabour, Nicholas Frosst

Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models

Jesse Engel, Matthew Hoffman, Adam Roberts

Certifying Some Distributional Robustness with Principled Adversarial Training

Aman Sinha, Hongseok Namkoong, John Duchi

Neural Map: Structured Memory for Deep Reinforcement Learning

Emilio Parisotto, Ruslan Salakhutdinov

FearNet: Brain-Inspired Model for Incremental Learning

Ronald Kemker, Christopher Kanan

Memory-based Parameter Adaptation

Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia

Decision Boundary Analysis of Adversarial Examples

Warren He, Bo Li, Dawn Song

Action-dependent Control Variates for Policy Optimization via Stein Identity

Hao Liu*, Yihao Feng*, Yi Mao, Dengyong Zhou, Jian Peng

Few-Shot Learning with Graph Neural Networks

Victor Garcia Satorras, Joan Bruna Estrach

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering

Shuohang Wang, Mo Yu, Jing Jiang, Wei Zhang, Xiaoxiao Guo

Activation Maximization Generative Adversarial Nets

Zhiming Zhou, Han Cai, Shu Rong, Yuxuan Song, Kan Ren

Certified Defenses against Adversarial Examples

Aditi Raghunathan, Jacob Steinhardt, Percy Liang

Learning a neural response metric for retinal prosthesis

Nishal P Shah, Sasidhar Madugula, EJ Chichilnisky, Yoram Singer, Jonathon Shlens

Kronecker-factored Curvature Approximations for Recurrent Neural Networks

James Martens, Jimmy Ba, Matt Johnson

Guide Actor-Critic for Continuous Control

Voot Tangkaratt, Abbas Abdolmaleki, Masashi Sugiyama

Global Optimality Conditions for Deep Neural Networks

Chulhee Yun, Suvrit Sra, Ali Jadbabaie

FusionNet: Fusing via Fully-aware Attention with Application to Machine Comprehension

Hsin-Yuan Huang, Chenguang Zhu, Yelong Shen, Weizhu Chen