Abstract is missing.
- TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement LearningGregory Farquhar, Tim Rocktäschel, Maximilian Igl, Shimon Whiteson. [doi]
- Proximal BackpropagationThomas Frerix, Thomas Möllenhoff, Michael Möller 0001, Daniel Cremers. [doi]
- Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement LearningTianmin Shu, Caiming Xiong, Richard Socher. [doi]
- Boosting Dilated Convolutional Networks with Mixed Tensor DecompositionsNadav Cohen, Ronen Tamari, Amnon Shashua. [doi]
- Divide-and-Conquer Reinforcement LearningDibya Ghosh, Avi Singh, Aravind Rajeswaran, Vikash Kumar, Sergey Levine. [doi]
- Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement LearningBenjamin Eysenbach, Shixiang Gu, Julian Ibarz, Sergey Levine. [doi]
- Hyperparameter optimization: a spectral approachElad Hazan, Adam R. Klivans, Yang Yuan. [doi]
- Memorization Precedes Generation: Learning Unsupervised GANs with Memory NetworksYoungjin Kim, Minjung Kim, Gunhee Kim. [doi]
- mixup: Beyond Empirical Risk MinimizationHongyi Zhang, Moustapha Cissé, Yann N. Dauphin, David Lopez-Paz. [doi]
- Interpretable Counting for Visual Question AnsweringAlexander Trott, Caiming Xiong, Richard Socher. [doi]
- Auto-Encoding Sequential Monte CarloTuan Anh Le, Maximilian Igl, Tom Rainforth, Tom Jin, Frank Wood. [doi]
- Empirical Risk Landscape Analysis for Understanding Deep Neural NetworksPan Zhou, Jiashi Feng. [doi]
- Overcoming Catastrophic Interference using Conceptor-Aided BackpropagationXu He, Herbert Jaeger. [doi]
- Online Learning Rate Adaptation with Hypergradient DescentAtilim Gunes Baydin, Robert Cornish, David Martínez-Rubio, Mark Schmidt, Frank Wood. [doi]
- Learning One-hidden-layer Neural Networks with Landscape DesignRong Ge 0001, Jason D. Lee, Tengyu Ma. [doi]
- Residual Connections Encourage Iterative InferenceStanislaw Jastrzebski, Devansh Arpit, Nicolas Ballas, Vikas Verma, Tong Che, Yoshua Bengio. [doi]
- Memory-based Parameter AdaptationPablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell. [doi]
- Stochastic Activation Pruning for Robust Adversarial DefenseGuneet S. Dhillon, Kamyar Azizzadenesheli, Zachary C. Lipton, Jeremy Bernstein, Jean Kossaifi, Aran Khanna, Animashree Anandkumar. [doi]
- Model-Ensemble Trust-Region Policy OptimizationThanard Kurutach, Ignasi Clavera, Yan Duan, Aviv Tamar, Pieter Abbeel. [doi]
- Multi-Scale Dense Networks for Resource Efficient Image ClassificationGao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Q. Weinberger. [doi]
- Guide Actor-Critic for Continuous ControlVoot Tangkaratt, Abbas Abdolmaleki, Masashi Sugiyama. [doi]
- Graph Attention NetworksPetar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio. [doi]
- Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning AlgorithmChelsea Finn, Sergey Levine. [doi]
- Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMsW. James Murdoch, Peter J. Liu, Bin Yu. [doi]
- Deep Rewiring: Training very sparse deep networksGuillaume Bellec, David Kappel, Wolfgang Maass 0001, Robert A. Legenstein. [doi]
- SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable DataAlon Brutzkus, Amir Globerson, Eran Malach, Shai Shalev-Shwartz. [doi]
- When is a Convolutional Filter Easy to Learn?Simon S. Du, Jason D. Lee, Yuandong Tian. [doi]
- Syntax-Directed Variational Autoencoder for Structured DataHanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, Le Song. [doi]
- Deep Learning for Physical Processes: Incorporating Prior Scientific KnowledgeEmmanuel de Bezenac, Arthur Pajot, Patrick Gallinari. [doi]
- Countering Adversarial Images using Input TransformationsChuan Guo, Mayank Rana, Moustapha Cissé, Laurens van der Maaten. [doi]
- Training Generative Adversarial Networks via Primal-Dual subgradient Methods: a Lagrangian Perspective on GaNXu Chen, Jiang Wang, Hao Ge. [doi]
- Neural Language Modeling by Jointly Learning Syntax and LexiconYikang Shen, Zhouhan Lin, Chin-Wei Huang, Aaron C. Courville. [doi]
- Consequentialist conditional cooperation in social dilemmas with imperfect informationAlexander Peysakhovich, Adam Lerer. [doi]
- Residual Loss Prediction: Reinforcement Learning With No Incremental FeedbackHal Daumé III, John Langford 0001, Amr Sharaf. [doi]
- Deep Active Learning for Named Entity RecognitionYanyao Shen, Hyokun Yun, Zachary C. Lipton, Yakov Kronrod, Animashree Anandkumar. [doi]
- Learning to Count Objects in Natural Images for Visual Question AnsweringYan Zhang, Jonathon Hare, Adam Prügel-Bennett. [doi]
- On the importance of single directions for generalizationAri S. Morcos, David G. T. Barrett, Neil C. Rabinowitz, Matthew Botvinick. [doi]
- Truncated horizon Policy Search: Combining Reinforcement Learning & Imitation LearningWen Sun 0002, J. Andrew Bagnell, Byron Boots. [doi]
- On the Convergence of Adam and BeyondSashank J. Reddi, Satyen Kale, Sanjiv Kumar. [doi]
- Active Neural LocalizationDevendra Singh Chaplot, Emilio Parisotto, Ruslan Salakhutdinov. [doi]
- Emergent Communication through NegotiationKris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z. Leibo, Karl Tuyls, Stephen Clark. [doi]
- Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task LearningSandeep Subramanian, Adam Trischler, Yoshua Bengio, Christopher J. Pal. [doi]
- Universal Agent for Disentangling Environments and TasksJiayuan Mao, Honghua Dong, Joseph J. Lim. [doi]
- Variational Network QuantizationJan Achterhold, Jan M. Köhler, Anke Schmeink, Tim Genewein. [doi]
- Learning an Embedding Space for Transferable Robot SkillsKarol Hausman, Jost Tobias Springenberg, Ziyu Wang 0001, Nicolas Heess, Martin A. Riedmiller. [doi]
- Kernel Implicit Variational InferenceJiaxin Shi, Shengyang Sun, Jun Zhu 0001. [doi]
- A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural NetworksBehnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro. [doi]
- Scalable Private Learning with PATENicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Úlfar Erlingsson. [doi]
- Mixed Precision Training of Convolutional Neural Networks using Integer OperationsDipankar Das 0002, Naveen Mellempudi, Dheevatsa Mudigere, Dhiraj D. Kalamkar, Sasikanth Avancha, Kunal Banerjee, Srinivas Sridharan 0002, Karthik Vaidyanathan, Bharat Kaul, Evangelos Georganas, Alexander Heinecke, Pradeep Dubey, Jesús Corbal, Nikita Shustrov, Roman Dubtsov, Evarist Fomenko, Vadim O. Pirogov. [doi]
- i-RevNet: Deep Invertible NetworksJörn-Henrik Jacobsen, Arnold W. M. Smeulders, Edouard Oyallon. [doi]
- Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain AdaptationPietro Morerio, Jacopo Cavazza, Vittorio Murino. [doi]
- Ask the Right Questions: Active Question Reformulation with Reinforcement LearningChristian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang. [doi]
- SEARNN: Training RNNs with global-local lossesRémi Leblond, Jean-Baptiste Alayrac, Anton Osokin, Simon Lacoste-Julien. [doi]
- Mixed Precision TrainingPaulius Micikevicius, Sharan Narang, Jonah Alben, Gregory F. Diamos, Erich Elsen, David García, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, Hao Wu. [doi]
- Adversarial Dropout RegularizationKuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada, Kate Saenko. [doi]
- The Implicit Bias of Gradient Descent on Separable DataDaniel Soudry, Elad Hoffer, Mor Shpigel Nacson, Nathan Srebro. [doi]
- Improving GAN Training via Binarized Representation Entropy (BRE) RegularizationYanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui, Ruitong Huang. [doi]
- Parallelizing Linear Recurrent Neural Nets Over Sequence LengthEric Martin, Chris Cundy. [doi]
- Activation Maximization Generative Adversarial NetsZhiming Zhou, Han Cai, Shu Rong, Yuxuan Song, Kan Ren, Weinan Zhang, Jun Wang 0012, Yong Yu 0001. [doi]
- A Deep Reinforced Model for Abstractive SummarizationRomain Paulus, Caiming Xiong, Richard Socher. [doi]
- Latent Constraints: Learning to Generate Conditionally from Unconditional Generative ModelsJesse Engel, Matthew Hoffman, Adam Roberts. [doi]
- A Hierarchical Model for Device PlacementAzalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc V. Le, Jeff Dean. [doi]
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution LayersJianbo Ye, Xin Lu, Zhe Lin 0001, James Z. Wang. [doi]
- Large scale distributed neural network training through online distillationRohan Anil, Gabriel Pereyra, Alexandre Passos, Róbert Ormándi, George E. Dahl, Geoffrey E. Hinton. [doi]
- Towards Image Understanding from Deep Compression Without DecodingRobert Torfason, Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc Van Gool. [doi]
- Reinforcement Learning on Web Interfaces using Workflow-Guided ExplorationEvan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, Percy Liang. [doi]
- A New Method of Region Embedding for Text ClassificationChao Qiao, Bo Huang, Guocheng Niu, Daren Li, Daxiang Dong, Wei He 0001, Dianhai Yu, Hua Wu 0003. [doi]
- Mastering the Dungeon: Grounded Language Learning by Mechanical Turker DescentZhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng, Alexander H. Miller, Arthur Szlam, Douwe Kiela, Jason Weston. [doi]
- Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network AccuracyAsit K. Mishra, Debbie Marr. [doi]
- Understanding image motion with group representationsAndrew Jaegle, Stephen Phillips, Daphne Ippolito, Kostas Daniilidis. [doi]
- Deep Sensing: Active Sensing using Multi-directional Recurrent Neural NetworksJinsung Yoon, William R. Zame, Mihaela van der Schaar. [doi]
- Multi-View Data Generation Without View SupervisionMickaël Chen, Ludovic Denoyer, Thierry Artières. [doi]
- Multi-level Residual Networks from Dynamical Systems ViewBo Chang, Lili Meng, Eldad Haber, Frederick Tung, David Begert. [doi]
- Learning to TeachYang Fan, Fei Tian, Tao Qin, Xiang-Yang Li 0001, Tie-Yan Liu. [doi]
- Ensemble Adversarial Training: Attacks and DefensesFlorian Tramèr, Alexey Kurakin, Nicolas Papernot, Ian J. Goodfellow, Dan Boneh, Patrick D. McDaniel. [doi]
- Matrix capsules with EM routingGeoffrey E. Hinton, Sara Sabour, Nicholas Frosst. [doi]
- Can Neural Networks Understand Logical Entailment?Richard Evans, David Saxton, David Amos, Pushmeet Kohli, Edward Grefenstette. [doi]
- A Neural Representation of Sketch DrawingsDavid Ha, Douglas Eck. [doi]
- Hierarchical Subtask Discovery with Non-Negative Matrix FactorizationAdam Christopher Earle, Andrew M. Saxe, Benjamin Rosman. [doi]
- Learning Robust Rewards with Adverserial Inverse Reinforcement LearningJustin Fu, Katie Luo, Sergey Levine. [doi]
- Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingCarlos Riquelme, George Tucker, Jasper Snoek. [doi]
- Initialization matters: Orthogonal Predictive State Recurrent Neural NetworksKrzysztof Choromanski, Carlton Downey, Byron Boots. [doi]
- FearNet: Brain-Inspired Model for Incremental LearningRonald Kemker, Christopher Kanan. [doi]
- Learning Discrete Weights Using the Local Reparameterization TrickOran Shayer, Dan Levi, Ethan Fetaya. [doi]
- Zero-Shot Visual ImitationDeepak Pathak, Parsa Mahmoudieh, Guanghao Luo, Pulkit Agrawal, Dian Chen, Yide Shentu, Evan Shelhamer, Jitendra Malik, Alexei A. Efros, Trevor Darrell. [doi]
- Learning Awareness ModelsBrandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gomez Colmenarejo, Alistair Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, Misha Denil. [doi]
- Mitigating Adversarial Effects Through RandomizationCihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, Alan L. Yuille. [doi]
- Unsupervised Representation Learning by Predicting Image RotationsSpyros Gidaris, Praveer Singh, Nikos Komodakis. [doi]
- Distributed Fine-tuning of Language Models on Private DataVadim Popov, Mikhail Kudinov, Irina Piontkovskaya, Petr Vytovtov, Alex Nevidomsky. [doi]
- Compositional Obverter Communication Learning from Raw Visual InputEdward Choi, Angeliki Lazaridou, Nando de Freitas. [doi]
- Decoupling the Layers in Residual NetworksRicky Fok, Aijun An, Zana Rashidi, Xiaogang Wang. [doi]
- SpectralNet: Spectral Clustering using Deep Neural NetworksUri Shaham, Kelly P. Stanton, Henry Li, Ronen Basri, Boaz Nadler, Yuval Kluger. [doi]
- Deep Neural Networks as Gaussian ProcessesJaehoon Lee, Yasaman Bahri, Roman Novak, Samuel S. Schoenholz, Jeffrey Pennington, Jascha Sohl-Dickstein. [doi]
- Not-So-Random FeaturesBrian Bullins, Cyril Zhang, Yi Zhang. [doi]
- Do GANs learn the distribution? Some Theory and EmpiricsSanjeev Arora, Andrej Risteski, Yi Zhang. [doi]
- The High-Dimensional Geometry of Binary Neural NetworksAlexander G. Anderson, Cory P. Berg. [doi]
- HexaConvEmiel Hoogeboom, Jorn W. T. Peters, Taco S. Cohen, Max Welling. [doi]
- Generalizing Across Domains via Cross-Gradient TrainingShiv Shankar, Vihari Piratla, Soumen Chakrabarti, Siddhartha Chaudhuri, Preethi Jyothi, Sunita Sarawagi. [doi]
- Learning to Share: simultaneous parameter tying and Sparsification in Deep LearningDejiao Zhang, Haozhu Wang, Mário A. T. Figueiredo, Laura Balzano. [doi]
- Adaptive Quantization of Neural NetworksSoroosh Khoram, Jing Li. [doi]
- Efficient Sparse-Winograd Convolutional Neural NetworksXingyu Liu, Jeff Pool, Song Han, William J. Dally. [doi]
- Learning Latent Permutations with Gumbel-Sinkhorn NetworksGonzalo E. Mena, David Belanger, Scott W. Linderman, Jasper Snoek. [doi]
- Temporal Difference Models: Model-Free Deep RL for Model-Based ControlVitchyr Pong, Shixiang Gu, Murtaza Dalal, Sergey Levine. [doi]
- Emergent Communication in a Multi-Modal, Multi-Step Referential GameKatrina Evtimova, Andrew Drozdov, Douwe Kiela, KyungHyun Cho. [doi]
- Learn to Pay AttentionSaumya Jetley, Nicholas A. Lord, Namhoon Lee, Philip H. S. Torr. [doi]
- Large Scale Optimal Transport and Mapping EstimationVivien Seguy, Bharath Bhushan Damodaran, Rémi Flamary, Nicolas Courty, Antoine Rolet, Mathieu Blondel. [doi]
- On the Discrimination-Generalization Tradeoff in GANsPengchuan Zhang, Qiang Liu 0001, Dengyong Zhou, Tao Xu, Xiaodong He 0001. [doi]
- Interactive Grounded Language Acquisition and Generalization in a 2D WorldHaonan Yu, Haichao Zhang, Wei Xu. [doi]
- SMASH: One-Shot Model Architecture Search through HyperNetworksAndrew Brock, Theodore Lim, James M. Ritchie, Nick Weston. [doi]
- Few-shot Autoregressive Density Estimation: Towards Learning to Learn DistributionsScott E. Reed, Yutian Chen, Thomas Paine, Aäron Van Den Oord, S. M. Ali Eslami, Danilo J. Rezende, Oriol Vinyals, Nando de Freitas. [doi]
- NerveNet: Learning Structured Policy with Graph Neural NetworksTingwu Wang, Renjie Liao, Jimmy Ba, Sanja Fidler. [doi]
- Fraternal DropoutKonrad Zolna, Devansh Arpit, Dendi Suhubdy, Yoshua Bengio. [doi]
- Variance Reduction for Policy Gradient with Action-Dependent Factorized BaselinesCathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M. Bayen, Sham Kakade, Igor Mordatch, Pieter Abbeel. [doi]
- Unbiased Online Recurrent OptimizationCorentin Tallec, Yann Ollivier. [doi]
- SCAN: Learning Hierarchical Compositional Visual ConceptsIrina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P. Burgess, Matko Bosnjak, Murray Shanahan, Matthew Botvinick, Demis Hassabis, Alexander Lerchner. [doi]
- Coulomb GANs: Provably Optimal Nash Equilibria via Potential FieldsThomas Unterthiner, Bernhard Nessler, Calvin Seward, Günter Klambauer, Martin Heusel, Hubert Ramsauer, Sepp Hochreiter. [doi]
- An efficient framework for learning sentence representationsLajanugen Logeswaran, Honglak Lee. [doi]
- Multi-Mention Learning for Reading Comprehension with Neural CascadesSwabha Swayamdipta, Ankur P. Parikh, Tom Kwiatkowski. [doi]
- Generative Models of Visually Grounded ImaginationRamakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy 0002. [doi]
- N2N learning: Network to Network Compression via Policy Gradient Reinforcement LearningAnubhav Ashok, Nicholas Rhinehart, Fares Beainy, Kris M. Kitani. [doi]
- Can recurrent neural networks warp time?Corentin Tallec, Yann Ollivier. [doi]
- Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly DetectionBo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Dae-Ki Cho, Haifeng Chen. [doi]
- Improving GANs Using Optimal TransportTim Salimans, Han Zhang, Alec Radford, Dimitris N. Metaxas. [doi]
- Reinforcement Learning Algorithm SelectionRomain Laroche, Raphaël Féraud. [doi]
- Learning to cluster in order to transfer across domains and tasksYen-Chang Hsu, Zhaoyang Lv, Zsolt Kira. [doi]
- Neural Sketch Learning for Conditional Program GenerationVijayaraghavan Murali, Letao Qi, Swarat Chaudhuri, Chris Jermaine. [doi]
- Generalizing Hamiltonian Monte Carlo with Neural NetworksDaniel Levy, Matthew D. Hoffman, Jascha Sohl-Dickstein. [doi]
- Lifelong Learning with Dynamically Expandable NetworksJaehong Yoon, Eunho Yang, Jeongtae Lee, Sung Ju Hwang. [doi]
- Spherical CNNsTaco S. Cohen, Mario Geiger, Jonas Köhler, Max Welling. [doi]
- WRPN: Wide Reduced-Precision NetworksAsit K. Mishra, Eriko Nurvitadhi, Jeffrey J. Cook, Debbie Marr. [doi]
- Quantitatively Evaluating GANs With Divergences Proposed for TrainingDaniel Jiwoong Im, He Ma, Graham W. Taylor, Kristin Branson. [doi]
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning ModelsWieland Brendel, Jonas Rauber, Matthias Bethge. [doi]
- Towards better understanding of gradient-based attribution methods for Deep Neural NetworksMarco Ancona, Enea Ceolini, Cengiz Öztireli, Markus Gross 0001. [doi]
- PixelNN: Example-based Image SynthesisAayush Bansal, Yaser Sheikh, Deva Ramanan. [doi]
- Predicting Floor-Level for 911 Calls with Neural Networks and Smartphone Sensor DataWilliam Falcon, Henning Schulzrinne. [doi]
- Identifying Analogies Across DomainsYedid Hoshen, Lior Wolf. [doi]
- Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their InteractionsSjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber. [doi]
- Self-ensembling for visual domain adaptationGeoffrey French, Michal Mackiewicz, Mark H. Fisher. [doi]
- Critical Percolation as a Framework to Analyze the Training of Deep NetworksZohar Ringel, Rodrigo Andrade de Bem. [doi]
- Deep Learning with Logged Bandit FeedbackThorsten Joachims, Adith Swaminathan, Maarten de Rijke. [doi]
- Backpropagation through the Void: Optimizing control variates for black-box gradient estimationWill Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud. [doi]
- FusionNet: Fusing via Fully-aware Attention with Application to Machine ComprehensionHsin-Yuan Huang, Chenguang Zhu, Yelong Shen, Weizhu Chen. [doi]
- Stochastic Variational Video PredictionMohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy H. Campbell, Sergey Levine. [doi]
- Fidelity-Weighted LearningMostafa Dehghani 0001, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf. [doi]
- Neural Map: Structured Memory for Deep Reinforcement LearningEmilio Parisotto, Ruslan Salakhutdinov. [doi]
- Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence LearningWei Ping, Kainan Peng, Andrew Gibiansky, Sercan Ömer Arik, Ajay Kannan, Sharan Narang, Jonathan Raiman, John Miller. [doi]
- Towards Neural Phrase-based Machine TranslationPo-Sen Huang, Chong Wang, Sitao Huang, Dengyong Zhou, Li Deng 0001. [doi]
- On the Information Bottleneck Theory of Deep LearningAndrew M. Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan D. Tracey, David Daniel Cox. [doi]
- Stabilizing Adversarial Nets with Prediction MethodsAbhay Kumar Yadav, Sohil Shah, Zheng Xu 0002, David W. Jacobs, Tom Goldstein. [doi]
- The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningAudrunas Gruslys, Will Dabney, Mohammad Gheshlaghi Azar, Bilal Piot, Marc G. Bellemare, Rémi Munos. [doi]
- Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion ControlGlen Berseth, Cheng Xie, Paul Cernek, Michiel van de Panne. [doi]
- Expressive power of recurrent neural networksValentin Khrulkov, Alexander Novikov, Ivan V. Oseledets. [doi]
- Breaking the Softmax Bottleneck: A High-Rank RNN Language ModelZhilin Yang, Zihang Dai, Ruslan Salakhutdinov, William W. Cohen. [doi]
- Automatically Inferring Data Quality for Spatiotemporal ForecastingSungyong Seo, Arash Mohegh, George Ban-Weiss, Yan Liu. [doi]
- Training and Inference with Integers in Deep Neural NetworksShuang Wu, Guoqi Li, Feng Chen, Luping Shi. [doi]
- Spatially Transformed Adversarial ExamplesChaowei Xiao, Jun-Yan Zhu, Bo Li 0044, Warren He, Mingyan Liu, Dawn Song. [doi]
- Active Learning for Convolutional Neural Networks: A Core-Set ApproachOzan Sener, Silvio Savarese. [doi]
- An Online Learning Approach to Generative Adversarial NetworksPaulina Grnarova, Kfir Y. Levy, Aurélien Lucchi, Thomas Hofmann, Andreas Krause 0001. [doi]
- A Framework for the Quantitative Evaluation of Disentangled RepresentationsCian Eastwood, Christopher K. I. Williams. [doi]
- Neural Speed Reading via Skim-RNNMin Joon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi. [doi]
- A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMsSanjeev Arora, Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli. [doi]
- Learning Parametric Closed-Loop Policies for Markov Potential GamesSergio Valcarcel Macua, Javier Zazo, Santiago Zazo. [doi]
- Fix your classifier: the marginal value of training the last weight layerElad Hoffer, Itay Hubara, Daniel Soudry. [doi]
- MGAN: Training Generative Adversarial Nets with Multiple GeneratorsQuan Hoang, Tu Dinh Nguyen, Trung Le, Dinh Q. Phung. [doi]
- Towards Synthesizing Complex Programs From Input-Output ExamplesXinyun Chen, Chang Liu, Dawn Song. [doi]
- Auto-Conditioned Recurrent Networks for Extended Complex Human Motion SynthesisYi Zhou, Zimo Li, Shuangjiu Xiao, Chong He, Zeng Huang, Hao Li 0015. [doi]
- Hierarchical Representations for Efficient Architecture SearchHanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, Koray Kavukcuoglu. [doi]
- Global Optimality Conditions for Deep Neural NetworksChulhee Yun, Suvrit Sra, Ali Jadbabaie. [doi]
- On Unifying Deep Generative ModelsZhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Eric P. Xing. [doi]
- GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial NetsJinsung Yoon, James Jordon, Mihaela van der Schaar. [doi]
- Distributed Prioritized Experience ReplayDan Horgan, John Quan, David Budden, Gabriel Barth-Maron, Matteo Hessel, Hado van Hasselt, David Silver. [doi]
- Gradient Estimators for Implicit ModelsYingzhen Li, Richard E. Turner. [doi]
- On the insufficiency of existing momentum schemes for Stochastic OptimizationRahul Kidambi, Praneeth Netrapalli, Prateek Jain 0002, Sham M. Kakade. [doi]
- A Simple Neural Attentive Meta-LearnerNikhil Mishra, Mostafa Rohaninejad, Xi Chen 0022, Pieter Abbeel. [doi]
- DORA The Explorer: Directed Outreaching Reinforcement Action-SelectionLior Fox, Leshem Choshen, Yonatan Loewenstein. [doi]
- Synthesizing realistic neural population activity patterns using Generative Adversarial NetworksManuel Molano-Mazon, Arno Onken, Eugenio Piasini, Stefano Panzeri. [doi]
- Combining Symbolic Expressions and Black-box Function Evaluations in Neural ProgramsForough Arabshahi, Sameer Singh, Animashree Anandkumar. [doi]
- Word translation without parallel dataGuillaume Lample, Alexis Conneau, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou. [doi]
- Emergence of grid-like representations by training recurrent neural networks to perform spatial localizationChristopher J. Cueva, Xue-Xin Wei. [doi]
- On the Expressive Power of Overlapping Architectures of Deep LearningOr Sharir, Amnon Shashua. [doi]
- Learning to Multi-Task by Active SamplingSahil Sharma, Ashutosh Kumar Jha, Parikshit Hegde, Balaraman Ravindran. [doi]
- Non-Autoregressive Neural Machine TranslationJiatao Gu, James Bradbury 0002, Caiming Xiong, Victor O. K. Li, Richard Socher. [doi]
- Continuous Adaptation via Meta-Learning in Nonstationary and Competitive EnvironmentsMaruan Al-Shedivat, Trapit Bansal, Yura Burda, Ilya Sutskever, Igor Mordatch, Pieter Abbeel. [doi]
- Policy Optimization by Genetic DistillationTanmay Gangwani, Jian Peng. [doi]
- Neural-Guided Deductive Search for Real-Time Program Synthesis from ExamplesAshwin Kalyan, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, Sumit Gulwani. [doi]
- Skip Connections Eliminate SingularitiesEmin Orhan, Xaq Pitkow. [doi]
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every StepWilliam Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed, Ian J. Goodfellow. [doi]
- Learning Approximate Inference Networks for Structured PredictionLifu Tu, Kevin Gimpel. [doi]
- Learning a neural response metric for retinal prosthesisNishal P. Shah, Sasidhar Madugula, E. J. Chichilnisky, Yoram Singer, Jonathon Shlens. [doi]
- Sensitivity and Generalization in Neural Networks: an Empirical StudyRoman Novak, Yasaman Bahri, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein. [doi]
- Unsupervised Machine Translation Using Monolingual Corpora OnlyGuillaume Lample, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato. [doi]
- MaskGAN: Better Text Generation via Filling in the _______William Fedus, Ian J. Goodfellow, Andrew M. Dai. [doi]
- Unsupervised Cipher Cracking Using Discrete GANsAidan N. Gomez, Sicong Huang, Ivan Zhang, Bryan M. Li, Muhammad Osama, Lukasz Kaiser. [doi]
- Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-ChipFeiwen Zhu, Jeff Pool, Michael Andersch, Jeremy Appleyard, Fung Xie. [doi]
- Learning Wasserstein EmbeddingsNicolas Courty, Rémi Flamary, Mélanie Ducoffe. [doi]
- Meta Learning Shared HierarchiesKevin Frans, Jonathan Ho, Xi Chen 0022, Pieter Abbeel, John Schulman. [doi]
- QANet: Combining Local Convolution with Global Self-Attention for Reading ComprehensionAdams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen 0010, Mohammad Norouzi 0002, Quoc V. Le. [doi]
- Emergent Translation in Multi-Agent CommunicationJason Lee, KyungHyun Cho, Jason Weston, Douwe Kiela. [doi]
- A DIRT-T Approach to Unsupervised Domain AdaptationRui Shu, Hung H. Bui, Hirokazu Narui, Stefano Ermon. [doi]
- Cascade Adversarial Machine Learning Regularized with a Unified EmbeddingTaesik Na, Jong Hwan Ko, Saibal Mukhopadhyay. [doi]
- Trust-PCL: An Off-Policy Trust Region Method for Continuous ControlOfir Nachum, Mohammad Norouzi 0002, Kelvin Xu, Dale Schuurmans. [doi]
- Measuring the Intrinsic Dimension of Objective LandscapesChunyuan Li, Heerad Farkhoor, Rosanne Liu, Jason Yosinski. [doi]
- Modular Continual Learning in a Unified Visual EnvironmentKevin T. Feigelis, Blue Sheffer, Daniel L. K. Yamins. [doi]
- Variational image compression with a scale hyperpriorJohannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston. [doi]
- Adaptive Dropout with Rademacher Complexity RegularizationKe Zhai 0001, Huan Wang. [doi]
- Boundary Seeking GANsR. Devon Hjelm, Athul Paul Jacob, Adam Trischler, Gerry Che, KyungHyun Cho, Yoshua Bengio. [doi]
- Parametrized Hierarchical Procedures for Neural ProgrammingRoy Fox, Richard Shin, Sanjay Krishnan, Ken Goldberg, Dawn Song, Ion Stoica. [doi]
- Smooth Loss Functions for Deep Top-k ClassificationLeonard Berrada, Andrew Zisserman, M. Pawan Kumar. [doi]
- A Scalable Laplace Approximation for Neural NetworksHippolyt Ritter, Aleksandar Botev, David Barber. [doi]
- Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity RegularizationOzsel Kilinc, Ismail Uysal. [doi]
- Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-BatchesYeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger Grosse. [doi]
- Regularizing and Optimizing LSTM Language ModelsStephen Merity, Nitish Shirish Keskar, Richard Socher. [doi]
- Generative networks as inverse problems with Scattering transformsTomás Angles, Stéphane Mallat. [doi]
- Leveraging Grammar and Reinforcement Learning for Neural Program SynthesisRudy Bunel, Matthew J. Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli. [doi]
- Progressive Growing of GANs for Improved Quality, Stability, and VariationTero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. [doi]
- Understanding Deep Neural Networks with Rectified Linear UnitsRaman Arora, Amitabh Basu, Poorya Mianjy, Anirbit Mukherjee. [doi]
- Dynamic Neural Program Embeddings for Program RepairKe Wang, Rishabh Singh, Zhendong Su. [doi]
- Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence ModelingTao Shen, Tianyi Zhou, Guodong Long, Jing Jiang 0002, Chengqi Zhang. [doi]
- Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network DesignYoav Levine, David Yakira, Nadav Cohen, Amnon Shashua. [doi]
- Debiasing Evidence Approximations: On Importance-weighted Autoencoders and Jackknife Variational InferenceSebastian Nowozin. [doi]
- Alternating Multi-bit Quantization for Recurrent Neural NetworksChen Xu, Jianqiang Yao, Zhouchen Lin, Wenwu Ou, Yuanbin Cao, Zhirong Wang, Hongbin Zha. [doi]
- Natural Language Inference over Interaction SpaceYichen Gong, Heng Luo, Jian Zhang. [doi]
- Generating Wikipedia by Summarizing Long SequencesPeter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, Noam Shazeer. [doi]
- Hierarchical Density Order EmbeddingsBen Athiwaratkun, Andrew Gordon Wilson. [doi]
- DCN+: Mixed Objective And Deep Residual Coattention for Question AnsweringCaiming Xiong, Victor Zhong, Richard Socher. [doi]
- Attacking Binarized Neural NetworksAngus Galloway, Graham W. Taylor, Medhat Moussa. [doi]
- Certifying Some Distributional Robustness with Principled Adversarial TrainingAman Sinha, Hongseok Namkoong, John C. Duchi. [doi]
- Maximum a Posteriori Policy OptimisationAbbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa, Rémi Munos, Nicolas Heess, Martin A. Riedmiller. [doi]
- Towards Reverse-Engineering Black-Box Neural NetworksSeong Joon Oh, Max Augustin, Mario Fritz, Bernt Schiele. [doi]
- Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled DiversityTianyi Zhou, Jeff A. Bilmes. [doi]
- Twin Networks: Matching the Future for Sequence GenerationDmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Adam Trischler, Chris Pal, Yoshua Bengio. [doi]
- Learning a Generative Model for Validity in Complex Discrete StructuresDavid Janz, Jos van der Westhuizen, Brooks Paige, Matt J. Kusner, José Miguel Hernández-Lobato. [doi]
- Robustness of Classifiers to Universal Perturbations: A Geometric PerspectiveSeyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, Stefano Soatto. [doi]
- Compositional Attention Networks for Machine ReasoningDrew A. Hudson, Christopher D. Manning. [doi]
- Depthwise Separable Convolutions for Neural Machine TranslationLukasz Kaiser, Aidan N. Gomez, François Chollet. [doi]
- Training GANs with OptimismConstantinos Daskalakis, Andrew Ilyas, Vasilis Syrgkanis, Haoyang Zeng. [doi]
- TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement LearningArtemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox. [doi]
- Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator AbstractionDa Xiao, Jo-Yu Liao, Xingyuan Yuan. [doi]
- Learning how to explain neural networks: PatternNet and PatternAttributionPieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan, Been Kim, Sven Dähne. [doi]
- Synthetic and Natural Noise Both Break Neural Machine TranslationYonatan Belinkov, Yonatan Bisk. [doi]
- Multi-Task Learning for Document Ranking and Query SuggestionWasi Uddin Ahmad, Kai-Wei Chang, Hongning Wang. [doi]
- Intrinsic Motivation and Automatic Curricula via Asymmetric Self-PlaySainbayar Sukhbaatar, Zeming Lin, Ilya Kostrikov, Gabriel Synnaeve, Arthur Szlam, Rob Fergus. [doi]
- On the regularization of Wasserstein GANsHenning Petzka, Asja Fischer, Denis Lukovnikov. [doi]
- Learning Sparse Neural Networks through L_0 RegularizationChristos Louizos, Max Welling, Diederik P. Kingma. [doi]
- Certified Defenses against Adversarial ExamplesAditi Raghunathan, Jacob Steinhardt, Percy Liang. [doi]
- Model compression via distillation and quantizationAntonio Polino, Razvan Pascanu, Dan Alistarh. [doi]
- Loss-aware Weight Quantization of Deep NetworksLu Hou, James T. Kwok. [doi]
- Communication Algorithms via Deep LearningHyeji Kim, Yihan Jiang, Ranvir Rana, Sreeram Kannan, Sewoong Oh, Pramod Viswanath. [doi]
- Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural NetworksShankar Krishnan, Ying Xiao, Rif A. Saurous. [doi]
- Learning Sparse Latent Representations with the Deep Copula Information BottleneckAleksander Wieczorek, Mario Wieser, Damian Murezzan, Volker Roth 0001. [doi]
- CausalGAN: Learning Causal Implicit Generative Models with Adversarial TrainingMurat Kocaoglu, Christopher Snyder, Alexandros G. Dimakis, Sriram Vishwanath. [doi]
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed TrainingYujun Lin, Song Han, Huizi Mao, Yu Wang 0002, Bill Dally. [doi]
- Boosting the Actor with Dual CriticBo Dai, Albert Shaw, Niao He, Lihong Li 0001, Le Song. [doi]
- Monotonic Chunkwise AttentionChung-Cheng Chiu, Colin Raffel. [doi]
- Compressing Word Embeddings via Deep Compositional Code LearningRaphael Shu, Hideki Nakayama. [doi]
- Variational Inference of Disentangled Latent Concepts from Unlabeled ObservationsAbhishek Kumar 0001, Prasanna Sattigeri, Avinash Balakrishnan. [doi]
- Eigenoption Discovery through the Deep Successor RepresentationMarlos C. Machado, Clemens Rosenbaum, Xiaoxiao Guo, Miao Liu, Gerald Tesauro, Murray Campbell. [doi]
- Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional MappingsKangwook Lee, Hoon Kim, Changho Suh. [doi]
- cGANs with Projection DiscriminatorTakeru Miyato, Masanori Koyama. [doi]
- Enhancing The Reliability of Out-of-distribution Image Detection in Neural NetworksShiyu Liang, Yixuan Li, R. Srikant. [doi]
- Variational Message Passing with Structured Inference NetworksWu Lin, Nicolas Hubacher, Mohammad Emtiyaz Khan. [doi]
- Simulating Action Dynamics with Neural Process NetworksAntoine Bosselut, Omer Levy, Ari Holtzman, Corin Ennis, Dieter Fox, Yejin Choi. [doi]
- Don't Decay the Learning Rate, Increase the Batch SizeSamuel L. Smith, Pieter-Jan Kindermans, Chris Ying, Quoc V. Le. [doi]
- Sobolev GANYoussef Mroueh, Chun-Liang Li, Tom Sercu, Anant Raj, Yu Cheng. [doi]
- Deep Learning as a Mixed Convex-Combinatorial Optimization ProblemAbram L. Friesen, Pedro M. Domingos. [doi]
- Gaussian Process Behaviour in Wide Deep Neural NetworksAlexander G. de G. Matthews, Jiri Hron, Mark Rowland, Richard E. Turner, Zoubin Ghahramani. [doi]
- Learning Differentially Private Recurrent Language ModelsH. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang 0001. [doi]
- Variational Continual LearningCuong V. Nguyen, Yingzhen Li, Thang D. Bui, Richard E. Turner. [doi]
- Latent Space Oddity: on the Curvature of Deep Generative ModelsGeorgios Arvanitidis, Lars Kai Hansen, Søren Hauberg. [doi]
- The power of deeper networks for expressing natural functionsDavid Rolnick, Max Tegmark. [doi]
- Meta-Learning for Semi-Supervised Few-Shot ClassificationMengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. [doi]
- Memory Architectures in Recurrent Neural Network Language ModelsDani Yogatama, Yishu Miao, Gábor Melis, Wang Ling, Adhiguna Kuncoro, Chris Dyer, Phil Blunsom. [doi]
- A Bayesian Perspective on Generalization and Stochastic Gradient DescentSamuel L. Smith, Quoc V. Le. [doi]
- Deep Complex NetworksChiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, João Felipe Santos, Soroush Mehri, Negar Rostamzadeh, Yoshua Bengio, Christopher J. Pal. [doi]
- Skip RNN: Learning to Skip State Updates in Recurrent Neural NetworksVíctor Campos, Brendan Jou, Xavier Giró i Nieto, Jordi Torres, Shih-Fu Chang. [doi]
- Temporally Efficient Deep Learning with SpikesPeter O'Connor, Efstratios Gavves, Matthias Reisser, Max Welling. [doi]
- Memory Augmented Control NetworksArbaaz Khan, Clark Zhang, Nikolay Atanasov, Konstantinos Karydis, Vijay Kumar 0001, Daniel D. Lee. [doi]
- Semantic Interpolation in Implicit ModelsYannic Kilcher, Aurélien Lucchi, Thomas Hofmann. [doi]
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement LearningRajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, Andrew McCallum. [doi]
- Spectral Normalization for Generative Adversarial NetworksTakeru Miyato, Toshiki Kataoka, Masanori Koyama, Yuichi Yoshida. [doi]
- Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal ExplorationAlexandre Péré, Sébastien Forestier, Olivier Sigaud, Pierre-Yves Oudeyer. [doi]
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance SamplingJie Chen, Tengfei Ma, Cao Xiao. [doi]
- Training wide residual networks for deployment using a single bit for each weightMark D. McDonnell. [doi]
- Towards Deep Learning Models Resistant to Adversarial AttacksAleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu. [doi]
- Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via RankingAleksandar Bojchevski, Stephan Günnemann. [doi]
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic ForecastingYaguang Li, Rose Yu, Cyrus Shahabi, Yan Liu 0002. [doi]
- Wavelet Pooling for Convolutional Neural NetworksTravis Williams, Robert Li. [doi]
- On the State of the Art of Evaluation in Neural Language ModelsGábor Melis, Chris Dyer, Phil Blunsom. [doi]
- The Kanerva Machine: A Generative Distributed MemoryYan Wu, Greg Wayne, Alex Graves, Timothy P. Lillicrap. [doi]
- Kronecker-factored Curvature Approximations for Recurrent Neural NetworksJames Martens, Jimmy Ba, Matt Johnson. [doi]
- Recasting Gradient-Based Meta-Learning as Hierarchical BayesErin Grant, Chelsea Finn, Sergey Levine, Trevor Darrell, Thomas L. Griffiths. [doi]
- Learning Intrinsic Sparse Structures within Long Short-Term MemoryWei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang, Wenhan Wang, Fang Liu, Bin Hu, Yiran Chen, Hai Li 0001. [doi]
- Detecting Statistical Interactions from Neural Network WeightsMichael Tsang, Dehua Cheng, Yan Liu 0002. [doi]
- WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic ModelingHao Zhang, Bo Chen 0001, Dandan Guo, Mingyuan Zhou. [doi]
- Demystifying MMD GANsMikolaj Binkowski, Dougal J. Sutherland, Michael Arbel, Arthur Gretton. [doi]
- Routing Networks: Adaptive Selection of Non-Linear Functions for Multi-Task LearningClemens Rosenbaum, Tim Klinger, Matthew Riemer. [doi]
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial ExamplesYang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman. [doi]
- Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual EffectXiang Wei, Boqing Gong, Zixia Liu, Wei Lu 0010, Liqiang Wang. [doi]
- Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer OrderingElliot Meyerson, Risto Miikkulainen. [doi]
- An image representation based convolutional network for DNA classificationBojian Yin, Marleen Balvert, Davide Zambrano, Alexander Schönhuth, Sander M. Bohte. [doi]
- AmbientGAN: Generative models from lossy measurementsAshish Bora, Eric Price, Alexandros G. Dimakis. [doi]
- Noisy Networks For ExplorationMeire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Matteo Hessel, Ian Osband, Alex Graves, Volodymyr Mnih, Rémi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg. [doi]
- Learning to Represent Programs with GraphsMiltiadis Allamanis, Marc Brockschmidt, Mahmoud Khademi. [doi]
- Polar Transformer NetworksCarlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou, Kostas Daniilidis. [doi]
- Implicit Causal Models for Genome-wide Association StudiesDustin Tran, David M. Blei. [doi]
- Few-Shot Learning with Graph Neural NetworksVictor Garcia Satorras, Joan Bruna Estrach. [doi]
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative ModelsPouya Samangouei, Maya Kabkab, Rama Chellappa. [doi]
- Understanding Short-Horizon Bias in Stochastic Meta-OptimizationYuhuai Wu, Mengye Ren, Renjie Liao, Roger Grosse. [doi]
- Generating Natural Adversarial ExamplesZhengli Zhao, Dheeru Dua, Sameer Singh. [doi]
- Parameter Space Noise for ExplorationMatthias Plappert, Rein Houthooft, Prafulla Dhariwal, Szymon Sidor, Richard Y. Chen, Xi Chen 0022, Tamim Asfour, Pieter Abbeel, Marcin Andrychowicz. [doi]
- Critical Points of Linear Neural Networks: Analytical Forms and Landscape PropertiesYi Zhou, Yingbin Liang. [doi]
- Wasserstein Auto-EncodersIlya O. Tolstikhin, Olivier Bousquet, Sylvain Gelly, Bernhard Schölkopf. [doi]
- Learning From Noisy Singly-labeled DataAshish Khetan, Zachary C. Lipton, Animashree Anandkumar. [doi]
- VoiceLoop: Voice Fitting and Synthesis via a Phonological LoopYaniv Taigman, Lior Wolf, Adam Polyak, Eliya Nachmani. [doi]
- Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution SamplesKimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin. [doi]
- Imitation Learning from Visual Data with Multiple IntentionsAviv Tamar, Khashayar Rohanimanesh, Yinlam Chow, Chris Vigorito, Ben Goodrich, Michael Kahane, Derik Pridmore. [doi]
- Learning from Between-class Examples for Deep Sound RecognitionYuji Tokozume, Yoshitaka Ushiku, Tatsuya Harada. [doi]
- Semi-parametric topological memory for navigationNikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun. [doi]
- Stochastic gradient descent performs variational inference, converges to limit cycles for deep networksPratik Chaudhari, Stefano Soatto. [doi]
- Unsupervised Neural Machine TranslationMikel Artetxe, Gorka Labaka, Eneko Agirre, KyungHyun Cho. [doi]
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question AnsweringShuohang Wang, Mo Yu, Jing Jiang 0001, Wei Zhang, Xiaoxiao Guo, Shiyu Chang, Zhiguo Wang, Tim Klinger, Gerald Tesauro, Murray Campbell. [doi]
- Evaluating the Robustness of Neural Networks: An Extreme Value Theory ApproachTsui-Wei Weng, Huan Zhang, Pin-Yu Chen, Jinfeng Yi, Dong Su, Yupeng Gao, Cho-Jui Hsieh, Luca Daniel. [doi]
- Divide and Conquer NetworksAlex Nowak, David Folqué, Joan Bruna. [doi]
- Decision Boundary Analysis of Adversarial ExamplesWarren He, Bo Li 0044, Dawn Song. [doi]
- Viterbi-based Pruning for Sparse Matrix with Fixed and High Index Compression RatioDongsoo Lee, Daehyun Ahn, Taesu Kim, Pierce I-Jen Chuang, Jae-Joon Kim. [doi]
- Action-dependent Control Variates for Policy Optimization via Stein IdentityHao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng 0001, Qiang Liu 0001. [doi]
- Thermometer Encoding: One Hot Way To Resist Adversarial ExamplesJacob Buckman, Aurko Roy, Colin Raffel, Ian J. Goodfellow. [doi]
- Learning Deep Mean Field Games for Modeling Large Population BehaviorJiachen Yang, Xiaojing Ye, Rakshit Trivedi, Huan Xu, Hongyuan Zha. [doi]
- Characterizing Adversarial Subspaces Using Local Intrinsic DimensionalityXingjun Ma, Bo Li 0044, Yisen Wang, Sarah M. Erfani, Sudanthi N. R. Wijewickrema, Grant Schoenebeck, Dawn Song, Michael E. Houle, James Bailey. [doi]
- Semantically Decomposing the Latent Spaces of Generative Adversarial NetworksChris Donahue, Zachary C. Lipton, Akshay Balsubramani, Julian McAuley. [doi]
- All-but-the-Top: Simple and Effective Postprocessing for Word RepresentationsJiaqi Mu, Pramod Viswanath. [doi]
- Espresso: Efficient Forward Propagation for Binary Deep Neural NetworksFabrizio Pedersoli, George Tzanetakis, Andrea Tagliasacchi. [doi]
- Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel InputAngeliki Lazaridou, Karl Moritz Hermann, Karl Tuyls, Stephen Clark. [doi]
- Distributed Distributional Deterministic Policy GradientsGabriel Barth-Maron, Matthew W. Hoffman, David Budden, Will Dabney, Dan Horgan, Dhruva TB, Alistair Muldal, Nicolas Heess, Timothy P. Lillicrap. [doi]
- The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic MappingsTomer Galanti, Lior Wolf, Sagie Benaim. [doi]
- Emergent Complexity via Multi-Agent CompetitionTrapit Bansal, Jakub Pachocki, Szymon Sidor, Ilya Sutskever, Igor Mordatch. [doi]