ICLR 2018

337 papers

Critical Percolation as a Framework to Analyze the Training of Deep Networks

Zohar Ringel, Rodrigo Andrade de Bem

Active Neural Localization

Devendra Singh Chaplot, Emilio Parisotto, Ruslan Salakhutdinov

Semantic Interpolation in Implicit Models

Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann

A Deep Reinforced Model for Abstractive Summarization

Romain Paulus, Caiming Xiong, Richard Socher

Active Learning for Convolutional Neural Networks: A Core-Set Approach

Ozan Sener, Silvio Savarese

Boundary Seeking GANs

R Devon Hjelm, Athul Paul Jacob, Adam Trischler, Gerry Che, Kyunghyun Cho

MaskGAN: Better Text Generation via Filling in the _______

William Fedus, Ian Goodfellow, Andrew M. Dai

Hierarchical Density Order Embeddings

Ben Athiwaratkun, Andrew Gordon Wilson

Semi-parametric topological memory for navigation

Nikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun

A Simple Neural Attentive Meta-Learner

Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel

The High-Dimensional Geometry of Binary Neural Networks

Alexander G. Anderson, Cory P. Berg

Memory Augmented Control Networks

Arbaaz Khan, Clark Zhang, Nikolay Atanasov, Konstantinos Karydis, Vijay Kumar

Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality

Xingjun Ma, Bo Li, Yisen Wang, Sarah M. Erfani, Sudanthi Wijewickrema

Emergence of grid-like representations by training recurrent neural networks to perform spatial localization

Christopher J. Cueva, Xue-xin Wei

Emergent Translation in Multi-Agent Communication

Jason Lee, Kyunghyun Cho, Jason Weston, Douwe Kiela

Imitation Learning from Visual Data with Multiple Intentions

Aviv Tamar, Khashayar Rohanimanesh, Yinlam Chow, Chris Vigorito, Ben Goodrich

Measuring the Intrinsic Dimension of Objective Landscapes

Chunyuan Li, Heerad Farkhoor, Rosanne Liu, Jason Yosinski

Depthwise Separable Convolutions for Neural Machine Translation

LUKASZ KAISER, Aidan N. Gomez, Francois Chollet

SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data

Alon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-shwartz

SpectralNet: Spectral Clustering using Deep Neural Networks

Uri Shaham, Kelly Stanton, Henry Li, Ronen Basri, Boaz Nadler

Generative networks as inverse problems with Scattering transforms

Tomás Angles, Stephane Mallat

Non-Autoregressive Neural Machine Translation

Jiatao Gu, James Bradbury, Caiming Xiong, Victor O.K. Li, Richard Socher

Emergent Complexity via Multi-Agent Competition

Trapit Bansal, Jakub Pachocki, Szymon Sidor, Ilya Sutskever, Igor Mordatch

Scalable Private Learning with PATE

Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar

Can Neural Networks Understand Logical Entailment?

Richard Evans, David Saxton, David Amos, Pushmeet Kohli, Edward Grefenstette

Learning Discrete Weights Using the Local Reparameterization Trick

Oran Shayer, Dan Levi, Ethan Fetaya

Training wide residual networks for deployment using a single bit for each weight

Mark D. McDonnell

Expressive power of recurrent neural networks

Valentin Khrulkov, Alexander Novikov, Ivan Oseledets

Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control

Glen Berseth, Cheng Xie, Paul Cernek, Michiel van de Panne

Learning a Generative Model for Validity in Complex Discrete Structures

Dave Janz, Jos van der Westhuizen, Brooks Paige, Matt Kusner, José Miguel Hernández-Lobato

DORA The Explorer: Directed Outreaching Reinforcement Action-Selection

Lior Fox, Leshem Choshen, Yonatan Loewenstein

The power of deeper networks for expressing natural functions

David Rolnick, Max Tegmark

Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling

Carlos Riquelme, George Tucker, Jasper Snoek

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension

Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen

Neural Speed Reading via Skim-RNN

Minjoon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi

Polar Transformer Networks

Carlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou, Kostas Daniilidis

A Neural Representation of Sketch Drawings

David Ha, Douglas Eck

A Framework for the Quantitative Evaluation of Disentangled Representations

Cian Eastwood, Christopher K. I. Williams

Learning Latent Permutations with Gumbel-Sinkhorn Networks

Gonzalo Mena, David Belanger, Scott Linderman, Jasper Snoek

Understanding image motion with group representations

Andrew Jaegle, Stephen Phillips, Daphne Ippolito, Kostas Daniilidis

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning

Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo

On the insufficiency of existing momentum schemes for Stochastic Optimization

Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

Angeliki Lazaridou, Karl Moritz Hermann, Karl Tuyls, Stephen Clark

TRUNCATED HORIZON POLICY SEARCH: COMBINING REINFORCEMENT LEARNING & IMITATION LEARNING

Wen Sun, J. Andrew Bagnell, Byron Boots

Auto-Encoding Sequential Monte Carlo

Tuan Anh Le, Maximilian Igl, Tom Rainforth, Tom Jin, Frank Wood

Learning Differentially Private Recurrent Language Models

H. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang

Automatically Inferring Data Quality for Spatiotemporal Forecasting

Sungyong Seo, Arash Mohegh, George Ban-Weiss, Yan Liu

Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions

Nadav Cohen, Ronen Tamari, Amnon Shashua

Self-ensembling for visual domain adaptation

Geoff French, Michal Mackiewicz, Mark Fisher

When is a Convolutional Filter Easy to Learn?

Simon S. Du, Jason D. Lee, Yuandong Tian

Learning Approximate Inference Networks for Structured Prediction

Lifu Tu, Kevin Gimpel

Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks

Shankar Krishnan, Ying Xiao, Rif. A. Saurous

Don't Decay the Learning Rate, Increase the Batch Size

Samuel L. Smith, Pieter-jan Kindermans, Chris Ying, Quoc V. Le

Loss-aware Weight Quantization of Deep Networks

Lu Hou, James T. Kwok

Learning Sparse Neural Networks through L_0 Regularization

Christos Louizos, Max Welling, Diederik P. Kingma

Wasserstein Auto-Encoders

Ilya Tolstikhin, Olivier Bousquet, Sylvain Gelly, Bernhard Schoelkopf

Natural Language Inference over Interaction Space

Yichen Gong, Heng Luo, Jian Zhang

Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge

Emmanuel de Bézenac, Arthur Pajot, Patrick Gallinari

Multi-level Residual Networks from Dynamical Systems View

Bo Chang, Lili Meng, Eldad Haber, Frederick Tung, David Begert

Multi-View Data Generation Without View Supervision

Mickaël Chen, Ludovic DENOYER, Thierry Artières

Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs

W. James Murdoch, Peter J. Liu, Bin Yu

Generative Models of Visually Grounded Imagination

Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy

MGAN: Training Generative Adversarial Nets with Multiple Generators

Quan Hoang, Tu Dinh Nguyen, Trung Le, Dinh Phung

Fraternal Dropout

Konrad Zolna, Devansh Arpit, Dendi Suhubdy, Yoshua Bengio

Countering Adversarial Images using Input Transformations

Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens van der Maaten

Temporally Efficient Deep Learning with Spikes

Peter O'Connor, Efstratios Gavves, Matthias Reisser, Max Welling

Compositional Obverter Communication Learning from Raw Visual Input

Edward Choi, Angeliki Lazaridou, Nando de Freitas

Fix your classifier: the marginal value of training the last weight layer

Elad Hoffer, Itay Hubara, Daniel Soudry

AmbientGAN: Generative models from lossy measurements

Ashish Bora, Eric Price, Alexandros G. Dimakis

A Bayesian Perspective on Generalization and Stochastic Gradient Descent

Samuel L. Smith and Quoc V. Le

TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning

Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach

Tsui-Wei Weng*, Huan Zhang*, Pin-Yu Chen, Jinfeng Yi, Dong Su

Variational Continual Learning

Cuong V. Nguyen, Yingzhen Li, Thang D. Bui, Richard E. Turner

Variational Network Quantization

Jan Achterhold, Jan Mathias Koehler, Anke Schmeink, Tim Genewein

Learning to Multi-Task by Active Sampling

Sahil Sharma*, Ashutosh Kumar Jha*, Parikshit S Hegde, Balaraman Ravindran

Multi-Scale Dense Networks for Resource Efficient Image Classification

Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten

Emergent Communication through Negotiation

Kris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z Leibo, Karl Tuyls

TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN

Xu Chen, Jiang Wang, Hao Ge

Cascade Adversarial Machine Learning Regularized with a Unified Embedding

Taesik Na, Jong Hwan Ko, Saibal Mukhopadhyay

VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop

Yaniv Taigman, Lior Wolf, Adam Polyak, Eliya Nachmani

Modular Continual Learning in a Unified Visual Environment

Kevin T. Feigelis, Blue Sheffer, Daniel L. K. Yamins

Synthetic and Natural Noise Both Break Neural Machine Translation

Yonatan Belinkov, Yonatan Bisk

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen

Backpropagation through the Void: Optimizing control variates for black-box gradient estimation

Will Grathwohl, Dami Choi, Yuhuai Wu, Geoff Roeder, David Duvenaud

Divide and Conquer Networks

Alex Nowak, David Folqué, Joan Bruna

Alternating Multi-bit Quantization for Recurrent Neural Networks

Chen Xu, Jianqiang Yao, Zhouchen Lin, Wenwu Ou, Yuanbin Cao

Gaussian Process Behaviour in Wide Deep Neural Networks

Alexander G. de G. Matthews, Jiri Hron, Mark Rowland, Richard E. Turner, Zoubin Ghahramani

N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning

Anubhav Ashok, Nicholas Rhinehart, Fares Beainy, Kris M. Kitani

Divide-and-Conquer Reinforcement Learning

Dibya Ghosh, Avi Singh, Aravind Rajeswaran, Vikash Kumar, Sergey Levine

Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization

Ozsel Kilinc, Ismail Uysal

Hierarchical Representations for Efficient Architecture Search

Hanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, Koray Kavukcuoglu

Learning from Between-class Examples for Deep Sound Recognition

Yuji Tokozume, Yoshitaka Ushiku, Tatsuya Harada

Learning to Teach

Yang Fan, Fei Tian, Tao Qin, Xiang-Yang Li, Tie-yan Liu

Towards Deep Learning Models Resistant to Adversarial Attacks

Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu

Espresso: Efficient Forward Propagation for Binary Deep Neural Networks

Fabrizio Pedersoli, George Tzanetakis, Andrea Tagliasacchi

CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training

Murat Kocaoglu, Christopher Snyder, Alexandros G. Dimakis, Sriram Vishwanath

Simulating Action Dynamics with Neural Process Networks

Antoine Bosselut, Omer Levy, Ari Holtzman, Corin Ennis, Dieter Fox

Sensitivity and Generalization in Neural Networks: an Empirical Study

Roman Novak, Yasaman Bahri, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-dickstein

On the State of the Art of Evaluation in Neural Language Models

Gábor Melis, Chris Dyer, Phil Blunsom

Thermometer Encoding: One Hot Way To Resist Adversarial Examples

Jacob Buckman, Aurko Roy, Colin Raffel, Ian Goodfellow