Table of Contents

• Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response FunctionsMatthew Mackay, Paul Vicol, Jonathan Lorraine, David Duvenaud, Roger B. Grosse. [doi]
• Meta-Learning Probabilistic Inference for PredictionJonathan Gordon 0003, John Bronskill, Matthias Bauer 0001, Sebastian Nowozin, Richard E. Turner. [doi]
• Learning Neural PDE Solvers with Convergence GuaranteesJun-Ting Hsieh, Shengjia Zhao, Stephan Eismann, Lucia Mirabella, Stefano Ermon. [doi]
• Hierarchical interpretations for neural network predictionsChandan Singh, W. James Murdoch, Bin Yu. [doi]
• Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization BoundsCenk Baykal, Lucas Liebenwein, Igor Gilitschenski, Dan Feldman, Daniela Rus. [doi]
• InstaGAN: Instance-aware Image-to-Image TranslationSangwoo Mo, Minsu Cho, Jinwoo Shin. [doi]
• Learning Finite State Representations of Recurrent Policy NetworksAnurag Koul, Alan Fern, Sam Greydanus. [doi]
• Attention, Learn to Solve Routing Problems!Wouter Kool, Herke van Hoof, Max Welling. [doi]
• Biologically-Plausible Learning Algorithms Can Scale to Large DatasetsWill Xiao, Honglin Chen, Qianli Liao, Tomaso A. Poggio. [doi]
• Optimal Completion Distillation for Sequence LearningSara Sabour, William Chan, Mohammad Norouzi 0002. [doi]
• Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous OutputsSachin Kumar, Yulia Tsvetkov. [doi]
• Learning Protein Structure with a Differentiable SimulatorJohn Ingraham, Adam J. Riesselman, Chris Sander, Debora S. Marks. [doi]
• signSGD with Majority Vote is Communication Efficient and Fault TolerantJeremy Bernstein, Jiawei Zhao, Kamyar Azizzadenesheli, Anima Anandkumar. [doi]
• Stochastic Optimization of Sorting Networks via Continuous RelaxationsAditya Grover, Eric Wang, Aaron Zweig, Stefano Ermon. [doi]
• Variational Smoothing in Recurrent Neural Network Language ModelsLingpeng Kong, Gábor Melis, Wang Ling, Lei Yu, Dani Yogatama. [doi]
• Sparse Dictionary Learning by Dynamical Neural NetworksTsung-Han Lin, Ping Tak Peter Tang. [doi]
• Variance Reduction for Reinforcement Learning in Input-Driven EnvironmentsHongzi Mao, Shaileshh Bojja Venkatakrishnan, Malte Schwarzkopf, Mohammad Alizadeh. [doi]
• Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RLAnusha Nagabandi, Chelsea Finn, Sergey Levine. [doi]
• Gradient descent aligns the layers of deep linear networksZiwei Ji, Matus Telgarsky. [doi]
• Multilingual Neural Machine Translation With Soft Decoupled EncodingXinyi Wang, Hieu Pham, Philip Arthur, Graham Neubig. [doi]
• AdaShift: Decorrelation and Convergence of Adaptive Learning Rate MethodsZhiming Zhou, Qingru Zhang, Guansong Lu, Hongwei Wang, Weinan Zhang 0001, Yong Yu 0001. [doi]
• Delta: Deep Learning Transfer using Feature Map with Attention for Convolutional NetworksXingjian Li, Haoyi Xiong, Hanchao Wang, Yuxuan Rao, Liping Liu, Jun Huan. [doi]
• ClariNet: Parallel Wave Generation in End-to-End Text-to-SpeechWei Ping, Kainan Peng, Jitong Chen. [doi]
• Practical lossless compression with latent variables using bits back codingJames Townsend, Thomas Bird, David Barber. [doi]
• CEM-RL: Combining evolutionary and gradient-based methods for policy searchAloïs Pourchot, Olivier Sigaud. [doi]
• Exploration by random network distillationYuri Burda, Harrison Edwards, Amos J. Storkey, Oleg Klimov. [doi]
• StrokeNet: A Neural Painting EnvironmentNingyuan Zheng, Yifan Jiang, Dingjiang Huang. [doi]
• Benchmarking Neural Network Robustness to Common Corruptions and PerturbationsDan Hendrycks, Thomas G. Dietterich. [doi]
• GO Gradient for Expectation-Based ObjectivesYulai Cong, Miaoyun Zhao, Ke Bai, Lawrence Carin. [doi]
• On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled DataNan Lu, Gang Niu, Aditya Krishna Menon, Masashi Sugiyama. [doi]
• On the Sensitivity of Adversarial Robustness to Input Data DistributionsGavin Weiguang Ding, Kry Yik-Chau Lui, Xiaomeng Jin, Luyu Wang, Ruitong Huang. [doi]
• SNAS: stochastic neural architecture searchSirui Xie, Hehui Zheng, Chunxiao Liu, Liang Lin. [doi]
• Generative Code Modeling with GraphsMarc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt, Oleksandr Polozov. [doi]
• Diversity is All You Need: Learning Skills without a Reward FunctionBenjamin Eysenbach, Abhishek Gupta 0004, Julian Ibarz, Sergey Levine. [doi]
• Variational Autoencoders with Jointly Optimized Latent Dependency StructureJiawei He, Yu Gong, Joseph Marino, Greg Mori, Andreas M. Lehrmann. [doi]
• Posterior Attention Models for Sequence to Sequence LearningShiv Shankar, Sunita Sarawagi. [doi]
• A Variational Inequality Perspective on Generative Adversarial NetworksGauthier Gidel, Hugo Berard, Gaëtan Vignoud, Pascal Vincent, Simon Lacoste-Julien. [doi]
• Multilingual Neural Machine Translation with Knowledge DistillationXu Tan, Yi Ren, Di He, Tao Qin, Zhou Zhao, Tie-Yan Liu. [doi]
• Modeling Uncertainty with Hedged Instance EmbeddingsSeong Joon Oh, Kevin P. Murphy, Jiyan Pan, Joseph Roth, Florian Schroff, Andrew C. Gallagher. [doi]
• A comprehensive, application-oriented study of catastrophic forgetting in DNNsB. Pfülb, A. Gepperth. [doi]
• How to train your MAMLAntreas Antoniou, Harrison Edwards, Amos J. Storkey. [doi]
• Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative ModelsEirikur Agustsson, Alexander Sage, Radu Timofte, Luc Van Gool. [doi]
• Explaining Image Classifiers by Counterfactual GenerationChun-Hao Chang, Elliot Creager, Anna Goldenberg, David Duvenaud. [doi]
• GAN Dissection: Visualizing and Understanding Generative Adversarial NetworksDavid Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba 0001. [doi]
• Do Deep Generative Models Know What They Don't Know?Eric T. Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Dilan Görür, Balaji Lakshminarayanan. [doi]
• PATE-GAN: Generating Synthetic Data with Differential Privacy GuaranteesJames Jordon, Jinsung Yoon, Mihaela van der Schaar. [doi]
• FlowQA: Grasping Flow in History for Conversational Machine ComprehensionHsin-Yuan Huang, Eunsol Choi, Wen-tau Yih. [doi]
• Adversarial Audio SynthesisChris Donahue, Julian J. McAuley, Miller S. Puckette. [doi]
• Identifying and Controlling Important Neurons in Neural Machine TranslationAnthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James R. Glass. [doi]
• Attentive Neural ProcessesHyunjik Kim, Andriy Mnih, Jonathan Schwarz, Marta Garnelo, S. M. Ali Eslami, Dan Rosenbaum, Oriol Vinyals, Yee Whye Teh. [doi]
• Generating High fidelity Images with subscale pixel Networks and Multidimensional UpscalingJacob Menick, Nal Kalchbrenner. [doi]
• Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural NetworksPatrick H. Chen, Si Si, Sanjiv Kumar, Yang Li, Cho-Jui Hsieh. [doi]
• Temporal Difference Variational Auto-EncoderKarol Gregor, George Papamakarios, Frederic Besse, Lars Buesing, Theophane Weber. [doi]
• On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to TrainingPing Li, Phan-Minh Nguyen. [doi]
• Learning a SAT Solver from Single-Bit SupervisionDaniel Selsam, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo de Moura, David L. Dill. [doi]
• Feature-Wise Bias AmplificationKlas Leino, Emily Black, Matt Fredrikson, Shayak Sen, Anupam Datta. [doi]
• Analyzing Inverse Problems with Invertible Neural NetworksLynton Ardizzone, Jakob Kruse, Carsten Rother, Ullrich Köthe. [doi]
• Slimmable Neural NetworksJiahui Yu, Linjie Yang, Ning Xu, Jianchao Yang, Thomas S. Huang. [doi]
• Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image RestorationXiaoshuai Zhang, Yiping Lu, Jiaying Liu 0001, Bin Dong. [doi]
• Information asymmetry in KL-regularized RLAlexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever, Dhruva Tirumala, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Yee Whye Teh, Razvan Pascanu, Nicolas Heess. [doi]
• BabyAI: A Platform to Study the Sample Efficiency of Grounded Language LearningMaxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, Lucas Willems, Chitwan Saharia, Thien Huu Nguyen, Yoshua Bengio. [doi]
• Spectral Inference Networks: Unifying Deep and Spectral LearningDavid Pfau, Stig Petersen, Ashish Agarwal, David G. T. Barrett, Kimberly L. Stachenfeld. [doi]
• Overcoming the Disentanglement vs Reconstruction Trade-off via Jacobian SupervisionJosé Lezama. [doi]
• Robustness May Be at Odds with AccuracyDimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner 0001, Aleksander Madry. [doi]
• Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionalityTaiji Suzuki. [doi]
• Coarse-grain Fine-grain Coattention Network for Multi-evidence Question AnsweringVictor Zhong, Caiming Xiong, Nitish Shirish Keskar, Richard Socher. [doi]
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian ProcessesRoman Novak, Lechao Xiao, Yasaman Bahri, Jaehoon Lee, Greg Yang, Jiri Hron, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein. [doi]
• Improving MMD-GAN Training with Repulsive Loss FunctionWei Wang 0133, Yuan Sun 0005, Saman K. Halgamuge. [doi]
• Non-vacuous Generalization Bounds at the ImageNet Scale: a PAC-Bayesian Compression ApproachWenda Zhou, Victor Veitch, Morgane Austern, Ryan P. Adams, Peter Orbanz. [doi]
• The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent StructureFrederic Koehler, Andrej Risteski. [doi]
• Learning concise representations for regression by evolving networks of treesWilliam G. La Cava, Tilak Raj Singh, James Taggart, Srinivas Suri, Jason H. Moore. [doi]
• AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active TrackingFangwei Zhong, Peng Sun, Wenhan Luo, Tingyun Yan, Yizhou Wang. [doi]
• There Are Many Consistent Explanations of Unlabeled Data: Why You Should AverageBen Athiwaratkun, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson. [doi]
• Towards Understanding Regularization in Batch NormalizationPing Luo 0002, Xinjiang Wang, Wenqi Shao, Zhanglin Peng. [doi]
• Post Selection Inference with Incomplete Maximum Mean Discrepancy EstimatorMakoto Yamada, Denny Wu, Yao-Hung Hubert Tsai, Hirofumi Ohta, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu. [doi]
• Learning Mixed-Curvature Representations in Product SpacesAlbert Gu, Frederic Sala, Beliz Gunel, Christopher Ré. [doi]
• Deep Decoder: Concise Image Representations from Untrained Non-convolutional NetworksReinhard Heckel, Paul Hand. [doi]
• Active Learning with Partial FeedbackPeiyun Hu, Zachary C. Lipton, Anima Anandkumar, Deva Ramanan. [doi]
• Rethinking the Value of Network PruningZhuang Liu 0003, Mingjie Sun, Tinghui Zhou, Gao Huang, Trevor Darrell. [doi]
• Visual Reasoning by Progressive Module NetworksSeung Wook Kim, Makarand Tapaswi, Sanja Fidler. [doi]
• Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetWieland Brendel, Matthias Bethge. [doi]
• Neural network gradient-based learning of black-box function interfacesAlon Jacovi, Guy Hadash, Einat Kermany, Boaz Carmeli, Ofer Lavi, George Kour, Jonathan Berant. [doi]
• A new dog learns old tricks: RL finds classic optimization algorithmsWeiwei Kong, Christopher Liaw, Aranyak Mehta, D. Sivakumar. [doi]
• Toward Understanding the Impact of Staleness in Distributed Machine LearningWei Dai 0003, Yi Zhou, Nanqing Dong, Hao Zhang 0025, Eric P. Xing. [doi]
• Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max LayersAlexander Shekhovtsov, Boris Flach. [doi]
• Analysing Mathematical Reasoning Abilities of Neural ModelsDavid Saxton, Edward Grefenstette, Felix Hill, Pushmeet Kohli. [doi]
• Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate PolicyYuan Xie, Boyi Liu, Qiang Liu 0001, Zhaoran Wang, Yuan Zhou, Jian Peng 0001. [doi]
• Learning To SimulateNataniel Ruiz, Samuel Schulter, Manmohan Chandraker. [doi]
• Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable RendererHsueh-Ti Derek Liu, Michael Tao, Chun-Liang Li, Derek Nowrouzezahrai, Alec Jacobson. [doi]
• Graph Wavelet Neural NetworkBingbing Xu, Huawei Shen, Qi Cao, Yunqi Qiu, Xueqi Cheng. [doi]
• Unsupervised Control Through Non-Parametric Discriminative RewardsDavid Warde-Farley, Tom Van de Wiele, Tejas Kulkarni, Catalin Ionescu, Steven Hansen, Volodymyr Mnih. [doi]
• Scalable Unbalanced Optimal Transport using Generative Adversarial NetworksKarren D. Yang, Caroline Uhler. [doi]
• Stable Opponent Shaping in Differentiable GamesAlistair Letcher, Jakob N. Foerster, David Balduzzi, Tim Rocktäschel, Shimon Whiteson. [doi]
• The role of over-parametrization in generalization of neural networksBehnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro. [doi]
• Discovery of Natural Language Concepts in Individual Units of CNNsSeil Na, Yo Joong Choe, Dong-hyun Lee, Gunhee Kim. [doi]
• Hindsight policy gradientsPaulo Rauber, Avinash Ummadisingu, Filipe Mutz, Jürgen Schmidhuber. [doi]
• Learning to Design RNAFrederic Runge, Danny Stoll, Stefan Falkner, Frank Hutter. [doi]
• Knowledge Flow: Improve Upon Your TeachersIou-Jen Liu, Jian Peng 0001, Alexander G. Schwing. [doi]
• ProMP: Proximal Meta-Policy SearchJonas Rothfuss, Dennis Lee, Ignasi Clavera, Tamim Asfour, Pieter Abbeel. [doi]
• Meta-Learning Update Rules for Unsupervised Representation LearningLuke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein. [doi]
• Large Scale Graph Learning From Smooth SignalsVassilis Kalofolias, Nathanaël Perraudin. [doi]
• From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical InferenceRandall Balestriero, Richard G. Baraniuk. [doi]
• Sliced Wasserstein Auto-EncodersSoheil Kolouri, Phillip E. Pope, Charles E. Martin, Gustavo K. Rohde. [doi]
• Learning Localized Generative Models for 3D Point Clouds via Graph ConvolutionDiego Valsesia, Giulia Fracastoro, Enrico Magli. [doi]
• Meta-Learning For Stochastic Gradient MCMCWenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato. [doi]
• Predict then Propagate: Graph Neural Networks meet Personalized PageRankJohannes Klicpera, Aleksandar Bojchevski, Stephan Günnemann. [doi]
• Supervised Policy Update for Deep Reinforcement LearningQuan Ho Vuong, Yiming Zhang, Keith W. Ross. [doi]
• Generative predecessor models for sample-efficient imitation learningYannick Schroecker, Mel Vecerík, Jonathan Scholz. [doi]
• Efficient Augmentation via Data SubsamplingMichael Kuchnik, Virginia Smith. [doi]
• Multi-Agent Dual LearningYiren Wang, Yingce Xia, Tianyu He, Fei Tian, Tao Qin, ChengXiang Zhai, Tie-Yan Liu. [doi]
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessRobert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, Wieland Brendel. [doi]
• Unsupervised Discovery of Parts, Structure, and DynamicsZhenjia Xu, Zhijian Liu, Chen Sun, Kevin Murphy 0002, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu 0001. [doi]
• Deep Graph InfomaxPetar Velickovic, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R. Devon Hjelm. [doi]
• Selfless Sequential LearningRahaf Aljundi, Marcus Rohrbach, Tinne Tuytelaars. [doi]
• Representation Degeneration Problem in Training Natural Language Generation ModelsJun Gao, Di He, Xu Tan, Tao Qin, Liwei Wang 0001, Tie-Yan Liu. [doi]
• Measuring Compositionality in Representation LearningJacob Andreas. [doi]
• Universal Successor Features ApproximatorsDiana Borsa, André Barreto, John Quan, Daniel J. Mankowitz, Hado van Hasselt, Rémi Munos, David Silver, Tom Schaul. [doi]
• Three Mechanisms of Weight Decay RegularizationGuodong Zhang, Chaoqi Wang, Bowen Xu, Roger B. Grosse. [doi]
• Small nonlinearities in activation functions create bad local minima in neural networksChulhee Yun, Suvrit Sra, Ali Jadbabaie. [doi]
• MisGAN: Learning from Incomplete Data with Generative Adversarial NetworksSteven Cheng-Xian Li, Bo Jiang, Benjamin M. Marlin. [doi]
• Transfer Learning for Sequences via Learning to CollocateWanyun Cui, Guangyu Zheng, Zhiqiang Shen, Sihang Jiang, Wei Wang 0009. [doi]
• Adversarial Domain Adaptation for Stable Brain-Machine InterfacesAli Farshchian, Juan Alvaro Gallego, Joseph Paul Cohen, Yoshua Bengio, Lee E. Miller, Sara A. Solla. [doi]
• Contingency-Aware Exploration in Reinforcement LearningJongwook Choi, Yijie Guo, Marcin Moczulski, Junhyuk Oh, Neal Wu, Mohammad Norouzi 0002, Honglak Lee. [doi]
• Eidetic 3D LSTM: A Model for Video Prediction and BeyondYunbo Wang, Lu Jiang 0004, Ming-Hsuan Yang, Li-Jia Li, Mingsheng Long, Li Fei-Fei 0001. [doi]
• Competitive experience replayHao Liu, Alexander Trott, Richard Socher, Caiming Xiong. [doi]
• From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction FollowingJustin Fu, Anoop Korattikara, Sergey Levine, Sergio Guadarrama. [doi]
• Lagging Inference Networks and Posterior Collapse in Variational AutoencodersJunxian He, Daniel Spokoyny, Graham Neubig, Taylor Berg-Kirkpatrick. [doi]
• Enabling Factorized Piano Music Modeling and Generation with the MAESTRO DatasetCurtis Hawthorne, Andriy Stasyuk, Adam Roberts, Ian Simon, Cheng-Zhi Anna Huang, Sander Dieleman, Erich Elsen, Jesse H. Engel, Douglas Eck. [doi]
• A Universal Music Translation NetworkNoam Mor, Lior Wolf, Adam Polyak, Yaniv Taigman. [doi]
• Dimensionality Reduction for Representing the Knowledge of Probabilistic ModelsMarc T. Law, Jake Snell, Amir Massoud Farahmand, Raquel Urtasun, Richard S. Zemel. [doi]
• KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial NetworksJames Jordon, Jinsung Yoon, Mihaela van der Schaar. [doi]
• Generalized Tensor Models for Recurrent Neural NetworksValentin Khrulkov, Oleksii Hrinchuk, Ivan V. Oseledets. [doi]
• Auxiliary Variational MCMCRaza Habib, David Barber. [doi]
• Wasserstein Barycenter Model EnsemblingPierre L. Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Cícero Nogueira dos Santos, Tom Sercu. [doi]
• Approximability of Discriminators Implies Diversity in GANsYu Bai, Tengyu Ma, Andrej Risteski. [doi]
• Training for Faster Adversarial Robustness Verification via Inducing ReLU StabilityKai Y. Xiao, Vincent Tjeng, Nur Muhammad (Mahi) Shafiullah, Aleksander Madry. [doi]
• Learning to Infer and Execute 3D Shape ProgramsYonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu 0001. [doi]
• Sample Efficient Imitation Learning for Continuous ControlFumihiro Sasaki, Tetsuya Yohira, Atsuo Kawaguchi. [doi]
• Kernel RNN Learning (KeRNL)Christopher Roth, Ingmar Kanitscheider, Ila Fiete. [doi]
• Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep NetworksCharbel Sakr, Naigang Wang, Chia-Yu Chen, Jungwook Choi, Ankur Agrawal, Naresh R. Shanbhag, Kailash Gopalakrishnan. [doi]
• Learning to Learn without Forgetting by Maximizing Transfer and Minimizing InterferenceMatthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, Gerald Tesauro. [doi]
• Relational Forward Models for Multi-Agent LearningAndrea Tacchetti, H. Francis Song, Pedro A. M. Mediano, Vinícius Flores Zambaldi, János Kramár, Neil C. Rabinowitz, Thore Graepel, Matthew Botvinick, Peter W. Battaglia. [doi]
• Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural NetworkDaehyun Ahn, Dongsoo Lee, Taesu Kim, Jae-Joon Kim. [doi]
• Texttovec: Deep Contextualized Neural autoregressive Topic Models of Language with Distributed Compositional PriorPankaj Gupta, Yatin Chaudhary, Florian Buettner, Hinrich Schütze 0001. [doi]
• Context-adaptive Entropy Model for End-to-end Optimized Image CompressionJooyoung Lee, Seunghyun Cho, Seung-Kwon Beack. [doi]
• RNNs implicitly implement tensor-product representationsR. Thomas McCoy, Tal Linzen, Ewan Dunbar, Paul Smolensky. [doi]
• Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content TransferOri Press, Tomer Galanti, Sagie Benaim, Lior Wolf. [doi]
• LayoutGAN: Generating Graphic Layouts with Wireframe DiscriminatorsJianan Li, Jimei Yang, Aaron Hertzmann, Jianming Zhang, Tingfa Xu. [doi]
• AntisymmetricRNN: A Dynamical System View on Recurrent Neural NetworksBo Chang, Minmin Chen, Eldad Haber, Ed H. Chi. [doi]
• Label super-resolution networksKolya Malkin, Caleb Robinson, Le Hou, Rachel Soobitsky, Jacob Czawlytko, Dimitris Samaras, Joel H. Saltz, Lucas Joppa, Nebojsa Jojic. [doi]
• Predicting the Generalization Gap in Deep Networks with Margin DistributionsYiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio. [doi]
• A Direct Approach to Robust Deep Learning Using Adversarial NetworksHuaXia Wang, Chun-Nam Yu. [doi]
• Music Transformer: Generating Music with Long-Term StructureCheng-Zhi Anna Huang, Ashish Vaswani, Jakob Uszkoreit, Ian Simon, Curtis Hawthorne, Noam Shazeer, Andrew M. Dai, Matthew D. Hoffman, Monica Dinculescu, Douglas Eck. [doi]
• Learning Procedural Abstractions and Evaluating Discrete Latent Temporal StructureKaran Goel, Emma Brunskill. [doi]
• Deep, Skinny Neural Networks are not Universal ApproximatorsJesse Johnson. [doi]
• Human-level Protein Localization with Convolutional Neural NetworksElisabeth Rumetshofer, Markus Hofmarcher, Clemens Röhrl, Sepp Hochreiter, Günter Klambauer. [doi]
• Information-Directed Exploration for Deep Reinforcement LearningNikolay Nikolov, Johannes Kirschner, Felix Berkenkamp, Andreas Krause 0001. [doi]
• Learning Factorized Multimodal RepresentationsYao-Hung Hubert Tsai, Paul Pu Liang, Amir Zadeh 0001, Louis-Philippe Morency, Ruslan Salakhutdinov. [doi]
• Learning Multi-Level Hierarchies with HindsightAndrew Levy, George Konidaris, Robert Platt Jr., Kate Saenko. [doi]
• Exemplar Guided Unsupervised Image-to-Image Translation with Semantic ConsistencyLiqian Ma, Xu Jia, Stamatios Georgoulis, Tinne Tuytelaars, Luc Van Gool. [doi]
• Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit RegularizationNavid Azizan Ruhi, Babak Hassibi. [doi]
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural NetworksJonathan Frankle, Michael Carbin. [doi]
• Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural NetworksJosé Oramas M., Kaili Wang, Tinne Tuytelaars. [doi]
• Deep reinforcement learning with relational inductive biasesVinícius Flores Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David P. Reichert, Timothy P. Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter W. Battaglia. [doi]
• Learnable Embedding Space for Efficient Neural Architecture CompressionShengcao Cao, Xiaofang Wang, Kris M. Kitani. [doi]
• A Statistical Approach to Assessing Neural Network RobustnessStefan Webb, Tom Rainforth, Yee Whye Teh, M. Pawan Kumar. [doi]
• Ordered Neurons: Integrating Tree Structures into Recurrent Neural NetworksYikang Shen, Shawn Tan, Alessandro Sordoni, Aaron C. Courville. [doi]
• Aggregated Momentum: Stability Through Passive DampingJames Lucas, Shengyang Sun, Richard S. Zemel, Roger B. Grosse. [doi]
• Don't let your Discriminator be fooledBrady Zhou, Philipp Krähenbühl. [doi]
• Unsupervised Learning of the Set of Local MaximaLior Wolf, Sagie Benaim, Tomer Galanti. [doi]
• Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and FluidsYunzhu Li, Jiajun Wu 0001, Russ Tedrake, Joshua B. Tenenbaum, Antonio Torralba 0001. [doi]
• Value Propagation NetworksNantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H. S. Torr, Nicolas Usunier. [doi]
• Learning to Learn with Conditional Class DependenciesXiang Jiang 0001, Mohammad Havaei, Farshid Varno, Gabriel Chartrand, Nicolas Chapados, Stan Matwin. [doi]
• Hierarchical RL Using an Ensemble of Proprioceptive Periodic PoliciesKenneth Marino, Abhinav Gupta 0001, Rob Fergus, Arthur Szlam. [doi]
• Synthetic Datasets for Neural Program SynthesisRichard Shin, Neel Kant, Kavi Gupta, Chris Bender, Brandon Trabucco, Rishabh Singh, Dawn Song. [doi]
• Smoothing the Geometry of Probabilistic Box EmbeddingsXiang Li, Luke Vilnis, Dongxu Zhang, Michael Boratko, Andrew McCallum. [doi]
• FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative ModelsWill Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud. [doi]
• GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language UnderstandingAlex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, Samuel R. Bowman. [doi]
• Graph HyperNetworks for Neural Architecture SearchChris Zhang, Mengye Ren, Raquel Urtasun. [doi]
• NOODL: Provable Online Dictionary Learning and Sparse CodingSirisha Rambhatla, Xingguo Li, Jarvis D. Haupt. [doi]
• Learning Embeddings into Entropic Wasserstein SpacesCharlie Frogner, Farzaneh Mirzazadeh, Justin Solomon. [doi]
• Bayesian Prediction of Future Street Scenes using Synthetic LikelihoodsApratim Bhattacharyya, Mario Fritz, Bernt Schiele. [doi]
• Generating Multiple Objects at Spatially Distinct LocationsTobias Hinz, Stefan Heinrich, Stefan Wermter. [doi]
• Boosting Robustness Certification of Neural NetworksGagandeep Singh, Timon Gehr, Markus Püschel, Martin T. Vechev. [doi]
• G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant SpaceQi Meng, Shuxin Zheng, Huishuai Zhang, Wei Chen 0034, Qiwei Ye, Zhi-Ming Ma, Nenghai Yu, Tie-Yan Liu. [doi]
• Towards GAN Benchmarks Which Require GeneralizationIshaan Gulrajani, Colin Raffel, Luke Metz. [doi]
• Multi-class classification without multi-class labelsYen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira. [doi]
• Fluctuation-dissipation relations for stochastic gradient descentSho Yaida. [doi]
• Deterministic Variational Inference for Robust Bayesian Neural NetworksAnqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner, José Miguel Hernández-Lobato, Alexander L. Gaunt. [doi]
• Function Space Particle Optimization for Bayesian Neural NetworksZiyu Wang, Tongzheng Ren, Jun Zhu 0001, Bo Zhang 0010. [doi]
• SOM-VAE: Interpretable Discrete Representation Learning on Time SeriesVincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, Gunnar Rätsch. [doi]
• L2-Nonexpansive Neural NetworksHaifeng Qian, Mark N. Wegman. [doi]
• Learning Factorized Representations for Open-Set Domain AdaptationMahsa Baktashmotlagh, Masoud Faraki, Tom Drummond, Mathieu Salzmann. [doi]
• Structured Neural SummarizationPatrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt. [doi]
• Learning to Represent EditsPengcheng Yin, Graham Neubig, Miltiadis Allamanis, Marc Brockschmidt, Alexander L. Gaunt. [doi]
• Time-Agnostic Prediction: Predicting Predictable Video FramesDinesh Jayaraman, Frederik Ebert, Alexei A. Efros, Sergey Levine. [doi]
• Deep Anomaly Detection with Outlier ExposureDan Hendrycks, Mantas Mazeika, Thomas G. Dietterich. [doi]
• Query-Efficient Hard-label Black-box Attack: An Optimization-based ApproachMinhao Cheng, Thong Le, Pin-Yu Chen, Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh. [doi]
• Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word VectorsVitalii Zhelezniak, Aleksandar Savkov, April Shen, Francesco Moramarco, Jack Flann, Nils Y. Hammerla. [doi]
• Distribution-Interpolation Trade off in Generative ModelsDamian Lesniak, Igor Sieradzki, Igor T. Podolak. [doi]
• Woulda, Coulda, Shoulda: Counterfactually-Guided Policy SearchLars Buesing, Theophane Weber, Yori Zwols, Nicolas Heess, Sébastien Racanière, Arthur Guez, Jean-Baptiste Lespiau. [doi]
• Deep Frank-Wolfe For Neural Network OptimizationLeonard Berrada, Andrew Zisserman, M. Pawan Kumar. [doi]
• Phase-Aware Speech Enhancement with Deep Complex U-NetHyeong-Seok Choi, Jang-Hyun Kim, Jaesung Huh, Adrian Kim, Jung-Woo Ha, Kyogu Lee. [doi]
• Deep learning generalizes because the parameter-function map is biased towards simple functionsGuillermo Valle Pérez, Chico Q. Camargo, Ard A. Louis. [doi]
• SGD Converges to Global Minimum in Deep Learning via Star-convex PathYi Zhou, Junjie Yang, Huishuai Zhang, Yingbin Liang, Vahid Tarokh. [doi]
• Spherical CNNs on Unstructured GridsChiyu Max Jiang, Jingwei Huang, Karthik Kashinath, Prabhat, Philip Marcus, Matthias Nießner. [doi]
• Towards the first adversarially robust neural network model on MNISTLukas Schott, Jonas Rauber, Matthias Bethge, Wieland Brendel. [doi]
• Complement Objective TrainingHao-Yun Chen, Pei-Hsin Wang, Chun-Hao Liu, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan. [doi]
• On Self Modulation for Generative Adversarial NetworksTing Chen, Mario Lucic, Neil Houlsby, Sylvain Gelly. [doi]
• Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic FailuresJonathan Uesato, Ananya Kumar, Csaba Szepesvári, Tom Erez, Avraham Ruderman, Keith Anderson, Krishnamurthy (Dj) Dvijotham, Nicolas Heess, Pushmeet Kohli. [doi]
• Learning To Solve Circuit-SAT: An Unsupervised Differentiable ApproachSaeed Amizadeh, Sergiy Matusevych, Markus Weimer. [doi]
• Learning to Remember More with Less MemorizationHung Le, Truyen Tran 0001, Svetha Venkatesh. [doi]
• Quasi-hyperbolic momentum and Adam for deep learningJerry Ma, Denis Yarats. [doi]
• Preferences Implicit in the State of the WorldRohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca D. Dragan. [doi]
• Bounce and Learn: Modeling Scene Dynamics with Real-World BouncesSenthil Purushwalkam, Abhinav Gupta 0001, Danny M. Kaufman, Bryan C. Russell. [doi]
• Learning to Understand Goal Specifications by Modelling RewardDzmitry Bahdanau, Felix Hill, Jan Leike, Edward Hughes, Seyed Arian Hosseini, Pushmeet Kohli, Edward Grefenstette. [doi]
• Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech RecognitionChun-Fu (Richard) Chen, Quanfu Fan, Neil Mallinar, Tom Sercu, Rogério Schmidt Feris. [doi]
• A Max-Affine Spline Perspective of Recurrent Neural NetworksZichao Wang 0001, Randall Balestriero, Richard G. Baraniuk. [doi]
• Revealing interpretable object representations from human behaviorCharles Y. Zheng, Francisco Pereira, Chris I. Baker, Martin N. Hebart. [doi]
• Marginalized Average Attentional Network for Weakly-Supervised LearningYuan Yuan, Yueming Lyu, Xi Shen, Ivor W. Tsang, Dit-Yan Yeung. [doi]
• Harmonic Unpaired Image-to-image TranslationRui Zhang, Tomas Pfister, Jia Li. [doi]
• Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical GuaranteesYuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma. [doi]
• Gradient Descent Provably Optimizes Over-parameterized Neural NetworksSimon S. Du, Xiyu Zhai, Barnabás Póczos, Aarti Singh. [doi]
• AutoLoss: Learning Discrete Schedule for Alternate OptimizationHaowen Xu, Hao Zhang 0025, Zhiting Hu, Xiaodan Liang, Ruslan Salakhutdinov, Eric P. Xing. [doi]
• Integer Networks for Data Compression with Latent-Variable ModelsJohannes Ballé, Nick Johnston, David Minnen. [doi]
• Learning deep representations by mutual information estimation and maximizationR. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, Yoshua Bengio. [doi]
• Feature Intertwiner for Object DetectionHongyang Li, Bo Dai, Shaoshuai Shi, Wanli Ouyang, Xiaogang Wang. [doi]
• LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videosElke Kirschbaum, Manuel Haußmann, Steffen Wolf, Hannah Sonntag, Justus Schneider, Shehabeldin Elzoheiry, Oliver Kann, Daniel Durstewitz, Fred A. Hamprecht. [doi]
• Visceral Machines: Risk-Aversion in Reinforcement Learning with Intrinsic Physiological RewardsDaniel J. McDuff, Ashish Kapoor. [doi]
• Improving Generalization and Stability of Generative Adversarial NetworksHoang Thanh-Tung, Truyen Tran 0001, Svetha Venkatesh. [doi]
• Imposing Category Trees Onto Word-Embeddings Using A Geometric ConstructionTiansi Dong, Christian Bauckhage, Hailong Jin, Juanzi Li, Olaf Cremers, Daniel Speicher, Armin B. Cremers, Jörg Zimmermann 0001. [doi]
• On Computation and Generalization of Generative Adversarial Networks under Spectrum ControlHaoming Jiang, Zhehui Chen, Minshuo Chen, Feng Liu, Dingding Wang 0001, Tuo Zhao. [doi]
• Dynamic Channel Pruning: Feature Boosting and SuppressionXitong Gao, Yiren Zhao, Lukasz Dudziak, Robert Mullins, Cheng-Zhong Xu 0001. [doi]
• Evaluating Robustness of Neural Networks with Mixed Integer ProgrammingVincent Tjeng, Kai Y. Xiao, Russ Tedrake. [doi]
• Amortized Bayesian Meta-LearningSachin Ravi, Alex Beatson. [doi]
• An analytic theory of generalization dynamics and transfer learning in deep linear networksAndrew K. Lampinen, Surya Ganguli. [doi]
• Efficiently testing local optimality and escaping saddles for ReLU networksChulhee Yun, Suvrit Sra, Ali Jadbabaie. [doi]
• Cost-Sensitive Robustness against Adversarial ExamplesXiao Zhang, David Evans 0001. [doi]
• Learning sparse relational transition modelsVictoria Xia, Zi Wang, Kelsey R. Allen, Tom Silver, Leslie Pack Kaelbling. [doi]
• Information Theoretic lower bounds on negative log likelihoodLuis Alfonso Lastras-Montaño. [doi]
• Robust Conditional Generative Adversarial NetworksGrigorios G. Chrysos, Jean Kossaifi, Stefanos Zafeiriou. [doi]
• On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step LengthStanislaw Jastrzebski, Zachary Kenton, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos J. Storkey. [doi]
• Interpolation-Prediction Networks for Irregularly Sampled Time SeriesSatya Narayan Shukla, Benjamin M. Marlin. [doi]
• ADef: an Iterative Algorithm to Construct Adversarial DeformationsRima Alaifari, Giovanni S. Alberti, Tandri Gauksson. [doi]
• The Deep Weight PriorAndrei Atanov, Arsenii Ashukha, Kirill Struminsky, Dmitry P. Vetrov, Max Welling. [doi]
• Towards Robust, Locally Linear Deep NetworksGuang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola. [doi]
• Poincare Glove: Hyperbolic Word EmbeddingsAlexandru Tifrea, Gary Bécigneul, Octavian-Eugen Ganea. [doi]
• PeerNets: Exploiting Peer Wisdom Against Adversarial AttacksJan Svoboda, Jonathan Masci, Federico Monti, Michael M. Bronstein, Leonidas J. Guibas. [doi]
• Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational AutoencoderCaio Corro, Ivan Titov. [doi]
• Capsule Graph Neural NetworkZhang Xinyi, Lihui Chen. [doi]
• DHER: Hindsight Experience Replay for Dynamic GoalsMeng Fang, Cheng Zhou, Bei Shi, Boqing Gong, Jia Xu, Tong Zhang. [doi]
• Diversity-Sensitive Conditional Generative Adversarial NetworksDingdong Yang, Seunghoon Hong, Yunseok Jang, Tianchen Zhao, Honglak Lee. [doi]
• Initialized Equilibrium Propagation for Backprop-Free TrainingPeter O'Connor, Efstratios Gavves, Max Welling. [doi]
• The Unusual Effectiveness of Averaging in GAN TrainingYasin Yazici, Chuan-Sheng Foo, Stefan Winkler 0001, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar 0001. [doi]
• Caveats for information bottleneck in deterministic scenariosArtemy Kolchinsky, Brendan D. Tracey, Steven Van Kuyk. [doi]
• Characterizing Audio Adversarial Examples Using Temporal DependencyZhuolin Yang, Bo Li 0026, Pin-Yu Chen, Dawn Song. [doi]
• Adaptive Posterior Learning: few-shot learning with a surprise-based memory moduleTiago Ramalho, Marta Garnelo. [doi]
• RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep NetworksXiuyuan Cheng, Qiang Qiu, A. Robert Calderbank, Guillermo Sapiro. [doi]
• Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input MaskingHaichuan Yang, Yuhao Zhu 0001, Ji Liu 0002. [doi]
• Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilienceVaishnavh Nagarajan, J. Zico Kolter. [doi]
• Verification of Non-Linear Specifications for Neural NetworksChongli Qin, Krishnamurthy (Dj) Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli. [doi]
• Neural TTS Stylization with Adversarial and Collaborative GamesShuang Ma, Daniel J. McDuff, Yale Song. [doi]
• BA-Net: Dense Bundle Adjustment NetworksChengzhou Tang, Ping Tan. [doi]
• Learning to Describe Scenes with ProgramsYunchao Liu, Zheng Wu, Daniel Ritchie, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu 0001. [doi]
• Policy Transfer with Strategy OptimizationWenhao Yu, C. Karen Liu, Greg Turk. [doi]
• Multiple-Attribute Text RewritingGuillaume Lample, Sandeep Subramanian, Eric Michael Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, Y-Lan Boureau. [doi]
• NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learningSirui Xie, Junning Huang, Lanxin Lei, Chunxiao Liu, Zheng Ma, Wei Zhang 0114, Liang Lin. [doi]
• code2seq: Generating Sequences from Structured Representations of CodeUri Alon 0002, Shaked Brody, Omer Levy, Eran Yahav. [doi]
• Quaternion Recurrent Neural NetworksTitouan Parcollet, Mirco Ravanelli, Mohamed Morchid, Georges Linarès, Chiheb Trabelsi, Renato de Mori, Yoshua Bengio. [doi]
• Kernel Change-point Detection with Auxiliary Deep Generative ModelsWei-Cheng Chang, Chun-Liang Li, Yiming Yang, Barnabás Póczos. [doi]
• Neural Probabilistic Motor Primitives for Humanoid ControlJosh Merel, Leonard Hasenclever, Alexandre Galashov, Arun Ahuja, Vu Pham, Greg Wayne, Yee Whye Teh, Nicolas Heess. [doi]
• Differentiable Learning-to-Normalize via Switchable NormalizationPing Luo 0002, Jiamin Ren, Zhanglin Peng, Ruimao Zhang, Jingyu Li. [doi]
• Soft Q-Learning with Mutual-Information RegularizationJordi Grau-Moya, Felix Leibfried, Peter Vrancx. [doi]
• On the Convergence of A Class of Adam-Type Algorithms for Non-Convex OptimizationXiangyi Chen, Sijia Liu 0001, Ruoyu Sun, Mingyi Hong. [doi]
• INVASE: Instance-wise Variable Selection using Neural NetworksJinsung Yoon, James Jordon, Mihaela van der Schaar. [doi]
• Adaptive Gradient Methods with Dynamic Bound of Learning RateLiangchen Luo, Yuanhao Xiong, Yan Liu, Xu Sun 0001. [doi]
• Preconditioner on Matrix Lie Group for SGDXi-Lin Li. [doi]
• Pay Less Attention with Lightweight and Dynamic ConvolutionsFelix Wu, Angela Fan, Alexei Baevski, Yann N. Dauphin, Michael Auli. [doi]
• Critical Learning Periods in Deep NetworksAlessandro Achille, Matteo Rovere, Stefano Soatto. [doi]
• Learning Exploration Policies for NavigationTao Chen, Saurabh Gupta 0001, Abhinav Gupta 0001. [doi]
• Dynamic Sparse Graph for Efficient Deep LearningLiu Liu, Lei Deng, Xing Hu, Maohua Zhu, Guoqi Li, Yufei Ding, Yuan Xie 0001. [doi]
• Meta-learning with differentiable closed-form solversLuca Bertinetto, João F. Henriques, Philip H. S. Torr, Andrea Vedaldi. [doi]
• Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere ConvolutionMin Liu, Fupin Yao, Chiho Choi, Ayan Sinha, Karthik Ramani. [doi]
• A rotation-equivariant convolutional neural network model of primary visual cortexAlexander S. Ecker, Fabian H. Sinz, Emmanouil Froudarakis, Paul G. Fahey, Santiago A. Cadena, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Andreas S. Tolias, Matthias Bethge. [doi]
• SPIGAN: Privileged Adversarial Learning from SimulationKuan-Hui Lee, German Ros, Jie Li, Adrien Gaidon. [doi]
• Disjoint Mapping Network for Cross-modal Matching of Voices and FacesYanDong Wen, Mahmoud Al Ismail, Weiyang Liu, Bhiksha Raj, Rita Singh. [doi]
• A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNsJack Lindsey, Samuel A. Ocko, Surya Ganguli, Stéphane Deny. [doi]
• Deep Layers as Stochastic SolversAdel Bibi, Bernard Ghanem, Vladlen Koltun, René Ranftl. [doi]
• Learning when to Communicate at Scale in Multiagent Cooperative and Competitive TasksAmanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar. [doi]
• Analysis of Quantized ModelsLu Hou, Ruiliang Zhang, James T. Kwok. [doi]
• Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data StreamsMohammad Kachuee, Orpaz Goldstein, Kimmo Kärkkäinen, Sajad Darabi, Majid Sarrafzadeh. [doi]
• A Closer Look at Few-shot ClassificationWei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, Jia-Bin Huang. [doi]
• Hierarchical Visuomotor Control of HumanoidsJosh Merel, Arun Ahuja, Vu Pham, Saran Tunyasuvunakool, Siqi Liu, Dhruva Tirumala, Nicolas Heess, Greg Wayne. [doi]
• Building Dynamic Knowledge Graphs from Text using Machine Reading ComprehensionRajarshi Das, Tsendsuren Munkhdalai, Xingdi Yuan, Adam Trischler, Andrew McCallum. [doi]
• Wizard of Wikipedia: Knowledge-Powered Conversational AgentsEmily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston. [doi]
• Learning Actionable Representations with Goal Conditioned PoliciesDibya Ghosh, Abhishek Gupta 0004, Sergey Levine. [doi]
• Adaptive Input Representations for Neural Language ModelingAlexei Baevski, Michael Auli. [doi]
• GANSynth: Adversarial Neural Audio SynthesisJesse H. Engel, Kumar Krishna Agrawal, Shuo Chen, Ishaan Gulrajani, Chris Donahue, Adam Roberts. [doi]
• Modeling the Long Term Future in Model-Based Reinforcement LearningNan Rosemary Ke, Amanpreet Singh, Ahmed Touati, Anirudh Goyal, Yoshua Bengio, Devi Parikh, Dhruv Batra. [doi]
• Adaptive Estimators Show Information Compression in Deep Neural NetworksIvan Chelombiev, Conor J. Houghton, Cian O'Donnell. [doi]
• Large Scale GAN Training for High Fidelity Natural Image SynthesisAndrew Brock, Jeff Donahue, Karen Simonyan. [doi]
• Learning Robust Representations by Projecting Superficial Statistics OutHaohan Wang, Zexue He, Zachary C. Lipton, Eric P. Xing. [doi]
• Learning Recurrent Binary/Ternary WeightsArash Ardakani, Zhengyun Ji, Sean C. Smithson, Brett H. Meyer, Warren J. Gross. [doi]
• The relativistic discriminator: a key element missing from standard GANAlexia Jolicoeur-Martineau. [doi]
• The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural SupervisionJiayuan Mao, Chuang Gan, Pushmeet Kohli, Joshua B. Tenenbaum, Jiajun Wu 0001. [doi]
• Large-Scale Answerer in Questioner's Mind for Visual Dialog Question GenerationSang-Woo Lee, Tong Gao, Sohee Yang, Jaejun Yoo, Jung-Woo Ha. [doi]
• How Powerful are Graph Neural Networks?Keyulu Xu, Weihua Hu, Jure Leskovec, Stefanie Jegelka. [doi]
• Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed InformationMohit Sharma, Arjun Sharma, Nicholas Rhinehart, Kris M. Kitani. [doi]
• Prior Convictions: Black-box Adversarial Attacks with Bandits and PriorsAndrew Ilyas, Logan Engstrom, Aleksander Madry. [doi]
• Bayesian Policy Optimization for Model UncertaintyGilwoo Lee, Brian Hou, Aditya Mandalika, Jeongseok Lee, Sanjiban Choudhury, Siddhartha S. Srinivasa. [doi]
• Learning Representations of Sets through Optimized PermutationsYan Zhang, Jonathon S. Hare, Adam Prügel-Bennett. [doi]
• Hierarchical Reinforcement Learning via Advantage-Weighted Information MaximizationTakayuki Osa, Voot Tangkaratt, Masashi Sugiyama. [doi]
• Global-to-local Memory Pointer Networks for Task-Oriented DialogueChien-Sheng Wu, Richard Socher, Caiming Xiong. [doi]
• Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional ClusteringXiaopeng Li, Zhourong Chen, Leonard K. M. Poon, Nevin L. Zhang. [doi]
• M^3RL: Mind-aware Multi-agent Management Reinforcement LearningTianmin Shu, Yuandong Tian. [doi]
• Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic TopologyBastian Rieck, Matteo Togninalli, Christian Bock, Michael Moor, Max Horn, Thomas Gumbsch, Karsten M. Borgwardt. [doi]
• Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size InputsRyan L. Murphy, Balasubramaniam Srinivasan 0003, Vinayak A. Rao, Bruno Ribeiro 0001. [doi]
• InfoBot: Transfer and Exploration via the Information BottleneckAnirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Hugo Larochelle, Matthew Botvinick, Yoshua Bengio, Sergey Levine. [doi]
• Learning a Meta-Solver for Syntax-Guided Program SynthesisXujie Si, Yuan Yang, Hanjun Dai, Mayur Naik, Le Song. [doi]
• What do you learn from context? Probing for sentence structure in contextualized word representationsIan Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R. Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das 0001, Ellie Pavlick. [doi]
• ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwareHan Cai, Ligeng Zhu, Song Han. [doi]
• Relaxed Quantization for Discretized Neural NetworksChristos Louizos, Matthias Reisser, Tijmen Blankevoort, Efstratios Gavves, Max Welling. [doi]
• Diversity and Depth in Per-Example Routing ModelsPrajit Ramachandran, Quoc V. Le. [doi]
• A Data-Driven and Distributed Approach to Sparse Signal Representation and RecoveryAli Mousavi, Gautam Dasarathy, Richard G. Baraniuk. [doi]
• Recall Traces: Backtracking Models for Efficient Reinforcement LearningAnirudh Goyal, Philemon Brakel, William Fedus, Soumye Singhal, Timothy P. Lillicrap, Sergey Levine, Hugo Larochelle, Yoshua Bengio. [doi]
• Generating Multi-Agent Trajectories using Programmatic Weak SupervisionEric Zhan, Stephan Zheng, Yisong Yue, Long Sha, Patrick Lucey. [doi]
• TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre TransferSicong Huang, Qiyang Li, Cem Anil, Xuchan Bao, Sageev Oore, Roger B. Grosse. [doi]
• Neural Program Repair by Jointly Learning to Localize and RepairMarko Vasic, Aditya Kanade, Petros Maniatis, David Bieber, Rishabh Singh. [doi]
• Conditional Network EmbeddingsBo Kang, Jefrey Lijffijt, Tijl De Bie. [doi]
• Deep Lagrangian Networks: Using Physics as Model Prior for Deep LearningMichael Lutter, Christian Ritter, Jan Peters 0001. [doi]
• Systematic Generalization: What Is Required and Can It Be Learned?Dzmitry Bahdanau, Shikhar Murty, Michael Noukhovitch, Thien Huu Nguyen, Harm de Vries, Aaron C. Courville. [doi]
• Recurrent Experience Replay in Distributed Reinforcement LearningSteven Kapturowski, Georg Ostrovski, John Quan, Rémi Munos, Will Dabney. [doi]
• An Empirical study of Binary Neural Networks' OptimisationMilad Alizadeh, Javier Fernández-Marqués, Nicholas D. Lane, Yarin Gal. [doi]
• Subgradient Descent Learns Orthogonal DictionariesYu Bai, Qijia Jiang, Ju Sun. [doi]
• Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural ImagesSanjana Srivastava, Guy Ben-Yosef, Xavier Boix. [doi]
• DyRep: Learning Representations over Dynamic GraphsRakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha. [doi]
• Learning Implicitly Recurrent CNNs Through Parameter SharingPedro H. P. Savarese, Michael Maire. [doi]
• Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq ModelsHuan Zhang, Hai Zhao. [doi]
• Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense TrafficMikael Henaff, Alfredo Canziani, Yann LeCun. [doi]
• CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the WildYang Zhang 0035, Hassan Foroosh, Philip David, Boqing Gong. [doi]
• How Important is a NeuronKedar Dhamdhere, Mukund Sundararajan, Qiqi Yan. [doi]
• Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness ControlRóbert Csordás, Jürgen Schmidhuber. [doi]
• Learning to Schedule Communication in Multi-agent Reinforcement LearningDaewoo Kim, Sangwoo Moon, David Hostallero, Wan Ju Kang, Taeyoung Lee, Kyunghwan Son, Yung Yi. [doi]
• No Training Required: Exploring Random Encoders for Sentence ClassificationJohn Wieting, Douwe Kiela. [doi]
• Visual Semantic Navigation using Scene PriorsWei Yang, Xiaolong Wang 0004, Ali Farhadi, Abhinav Gupta 0001, Roozbeh Mottaghi. [doi]
• Generalizable Adversarial Training via Spectral NormalizationFarzan Farnia, Jesse M. Zhang, David Tse. [doi]
• RelGAN: Relational Generative Adversarial Networks for Text GenerationWeili Nie, Nina Narodytska, Ankit Patel. [doi]
• Stochastic Prediction of Multi-Agent Interactions from Partial ObservationsChen Sun, Per Karlsson, Jiajun Wu 0001, Joshua B. Tenenbaum, Kevin Murphy 0002. [doi]
• Diffusion Scattering Transforms on GraphsFernando Gama, Alejandro Ribeiro, Joan Bruna. [doi]
• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-EncoderXiaodong Gu, KyungHyun Cho, Jung-Woo Ha, Sunghun Kim 0001. [doi]
• Large-Scale Study of Curiosity-Driven LearningYuri Burda, Harrison Edwards, Deepak Pathak, Amos J. Storkey, Trevor Darrell, Alexei A. Efros. [doi]
• Learning to Propagate Labels: Transductive Propagation Network for Few-Shot LearningYanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, Yi Yang. [doi]
• Towards Metamerism via Foveated Style TransferArturo Deza, Aditya Jonnalagadda, Miguel P. Eckstein. [doi]
• On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural NetworksYukun Ding, Jinglan Liu, Jinjun Xiong, Yiyu Shi. [doi]
• Execution-Guided Neural Program SynthesisXinyun Chen, Chang Liu 0021, Dawn Song. [doi]
• Per-Tensor Fixed-Point Quantization of the Back-Propagation AlgorithmCharbel Sakr, Naresh R. Shanbhag. [doi]
• Doubly Reparameterized Gradient Estimators for Monte Carlo ObjectivesGeorge Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison. [doi]
• Automatically Composing Representation Transformations as a Means for GeneralizationMichael Chang 0003, Abhishek Gupta 0004, Sergey Levine, Thomas L. Griffiths. [doi]
• Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement LearningAnusha Nagabandi, Ignasi Clavera, Simin Liu, Ronald S. Fearing, Pieter Abbeel, Sergey Levine, Chelsea Finn. [doi]
• A Generative Model For Electron PathsJohn Bradshaw, Matt J. Kusner, Brooks Paige, Marwin H. S. Segler, José Miguel Hernández-Lobato. [doi]
• Generative Question Answering: Learning to Answer the Whole QuestionMike Lewis, Angela Fan. [doi]
• Structured Adversarial Attack: Towards General Implementation and Better InterpretabilityKaidi Xu, Sijia Liu 0001, Pu Zhao, Pin-Yu Chen, Huan Zhang, Quanfu Fan, Deniz Erdogmus, Yanzhi Wang, Xue Lin. [doi]
• Preventing Posterior Collapse with delta-VAEsAli Razavi, Aäron Van Den Oord, Ben Poole, Oriol Vinyals. [doi]
• Random mesh projectors for inverse problemsKonik Kothari, Sidharth Gupta, Maarten V. De Hoop, Ivan Dokmanic. [doi]
• Top-Down Neural Model For FormulaeKarel Chvalovský. [doi]
• Learning to Make Analogies by Contrasting Abstract Relational StructureFelix Hill, Adam Santoro, David G. T. Barrett, Ari S. Morcos, Timothy P. Lillicrap. [doi]
• Unsupervised Domain Adaptation for Distance Metric LearningKihyuk Sohn, Wenling Shang, Xiang Yu 0002, Manmohan Chandraker. [doi]
• The Singular Values of Convolutional LayersHanie Sedghi, Vineet Gupta 0001, Philip M. Long. [doi]
• K for the Price of 1: Parameter-efficient Multi-task and Transfer LearningPramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew G. Howard. [doi]
• Improving the Generalization of Adversarial Training with Domain AdaptationChuanbiao Song, Kun He 0001, Liwei Wang 0001, John E. Hopcroft. [doi]
• Invariant and Equivariant Graph NetworksHaggai Maron, Heli Ben Hamu, Nadav Shamir, Yaron Lipman. [doi]
• Efficient Training on Very Large Corpora via Gramian EstimationWalid Krichene, Nicolas Mayoraz, Steffen Rendle, Li Zhang, Xinyang Yi, Lichan Hong, Ed H. Chi, John R. Anderson. [doi]
• Local SGD Converges Fast and Communicates LittleSebastian U. Stich. [doi]
• Robust estimation via Generative Adversarial NetworksChao Gao, Jiyi Liu, Yuan Yao, Weizhi Zhu. [doi]
• Latent Convolutional ModelsShahrukh Athar, Evgeny Burnaev, Victor S. Lempitsky. [doi]
• Regularized Learning for Domain Adaptation under Label ShiftsKamyar Azizzadenesheli, Anqi Liu, Fanny Yang, Animashree Anandkumar. [doi]
• Transferring Knowledge across Learning ProcessesSebastian Flennerhag, Pablo G. Moreno, Neil D. Lawrence, Andreas C. Damianou. [doi]
• Understanding Composition of Word Embeddings via Tensor DecompositionAbraham Frandsen, Rong Ge 0001. [doi]
• Unsupervised Adversarial Image ReconstructionArthur Pajot, Emmanuel de Bézenac, Patrick Gallinari. [doi]
• A Convergence Analysis of Gradient Descent for Deep Linear Neural NetworksSanjeev Arora, Nadav Cohen, Noah Golowich, Wei Hu. [doi]
• Probabilistic Recursive Reasoning for Multi-Agent Reinforcement LearningYing Wen, Yaodong Yang, Rui Luo, Jun Wang 0012, Wei Pan. [doi]
• Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with ApplicationsCarson Eisenach, Haichuan Yang, Ji Liu 0002, Han Liu. [doi]
• Meta-Learning with Latent Embedding OptimizationAndrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell. [doi]
• A2BCD: Asynchronous Acceleration with Optimal ComplexityRobert Hannah, Fei Feng, Wotao Yin. [doi]
• Excessive Invariance Causes Adversarial VulnerabilityJörn-Henrik Jacobsen, Jens Behrmann, Richard S. Zemel, Matthias Bethge. [doi]
• Self-Monitoring Navigation Agent via Auxiliary Progress EstimationChih-Yao Ma, Jiasen Lu, Zuxuan Wu, Ghassan Alregib, Zsolt Kira, Richard Socher, Caiming Xiong. [doi]
• Learning what and where to attendDrew Linsley, Dan Shiebler, Sven Eberhardt, Thomas Serre. [doi]
• signSGD via Zeroth-Order OracleSijia Liu 0001, Pin-Yu Chen, Xiangyi Chen, Mingyi Hong. [doi]
• Spreading vectors for similarity searchAlexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou. [doi]
• Learning from Positive and Unlabeled Data with a Selection BiasMasahiro Kato, Takeshi Teshima, Junya Honda. [doi]
• Multi-Domain Adversarial LearningAlice Schoenauer Sebag, Louise Heinrich, Marc Schoenauer, Michèle Sebag, Lani F. Wu, Steven J. Altschuler. [doi]
• ProbGAN: Towards Probabilistic GAN with Theoretical GuaranteesHao He, Hao Wang, Guang-He Lee, Yonglong Tian. [doi]
• Learning Self-Imitating Diverse PoliciesTanmay Gangwani, Qiang Liu 0001, Jian Peng 0001. [doi]
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex SpaceZhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, Jian Tang 0005. [doi]
• Learning what you can do before doing anythingOleh Rybkin, Karl Pertsch, Konstantinos G. Derpanis, Kostas Daniilidis, Andrew Jaegle. [doi]
• Multi-step Retriever-Reader Interaction for Scalable Open-domain Question AnsweringRajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum. [doi]
• Neural Graph Evolution: Towards Efficient Automatic Robot DesignTingwu Wang, Yuhao Zhou, Sanja Fidler, Jimmy Ba. [doi]
• Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged SolutionsZaiyi Chen, Zhuoning Yuan, Jinfeng Yi, Bowen Zhou, Enhong Chen, Tianbao Yang. [doi]
• Environment Probing Interaction PoliciesWenxuan Zhou, Lerrel Pinto, Abhinav Gupta 0001. [doi]
• L-Shapley and C-Shapley: Efficient Model Interpretation for Structured DataJianbo Chen, Le Song, Martin J. Wainwright, Michael I. Jordan. [doi]
• ALISTA: Analytic Weights Are As Good As Learned Weights in LISTAJialin Liu 0003, Xiaohan Chen, Zhangyang Wang, Wotao Yin. [doi]
• On the loss landscape of a class of deep neural networks with no bad local valleysQuynh Nguyen 0001, Mahesh Chandra Mukkamala, Matthias Hein 0001. [doi]
• DARTS: Differentiable Architecture SearchHanxiao Liu, Karen Simonyan, Yiming Yang. [doi]
• Combinatorial Attacks on Binarized Neural NetworksElias B. Khalil, Amrita Gupta, Bistra Dilkina. [doi]
• Max-MIG: an Information Theoretic Approach for Joint Learning from CrowdsPeng Cao, Yilun Xu, Yuqing Kong, Yizhou Wang. [doi]
• Solving the Rubik's Cube with Approximate Policy IterationStephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi. [doi]
• Reasoning About Physical Interactions with Object-Oriented Prediction and PlanningMichael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu 0001. [doi]
• Understanding and Improving Interpolation in Autoencoders via an Adversarial RegularizerDavid Berthelot, Colin Raffel, Aurko Roy, Ian J. Goodfellow. [doi]
• ProxQuant: Quantized Neural Networks via Proximal OperatorsYu Bai, Yu-Xiang Wang, Edo Liberty. [doi]
• Stable Recurrent ModelsJohn Miller, Moritz Hardt. [doi]
• Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural NetworkXuanqing Liu, Yao Li, Chongruo Wu, Cho-Jui Hsieh. [doi]
• Harmonizing Maximum Likelihood with GANs for Multimodal Conditional GenerationSoochan Lee, Junsoo Ha, Gunhee Kim. [doi]
• The Laplacian in RL: Learning Representations with Efficient ApproximationsYifan Wu, George Tucker, Ofir Nachum. [doi]
• LanczosNet: Multi-Scale Deep Graph Convolutional NetworksRenjie Liao, Zhizhen Zhao, Raquel Urtasun, Richard S. Zemel. [doi]
• Generating Liquid Simulations with Deformation-aware Neural NetworksLukas Prantl, Boris Bonev, Nils Thuerey. [doi]
• Trellis Networks for Sequence ModelingShaojie Bai, J. Zico Kolter, Vladlen Koltun. [doi]
• Unsupervised Hyper-alignment for Multilingual Word EmbeddingsJean Alaux, Edouard Grave, Marco Cuturi, Armand Joulin. [doi]
• Unsupervised Learning via Meta-LearningKyle Hsu, Sergey Levine, Chelsea Finn. [doi]
• Efficient Multi-Objective Neural Architecture Search via Lamarckian EvolutionThomas Elsken, Jan Hendrik Metzen, Frank Hutter. [doi]
• Learning to Navigate the WebIzzeddin Gur, Ulrich Rückert, Aleksandra Faust, Dilek Hakkani-Tür. [doi]
• Riemannian Adaptive Optimization MethodsGary Bécigneul, Octavian-Eugen Ganea. [doi]
• Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability DetectionTue Le, Tuan Nguyen, Trung Le, Dinh Q. Phung, Paul Montague, Olivier Y. de Vel, Lizhen Qu. [doi]
• Hyperbolic Attention NetworksÇaglar Gülçehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter W. Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas. [doi]
• STCN: Stochastic Temporal Convolutional NetworksEmre Aksan, Otmar Hilliges. [doi]
• Minimal Random Code Learning: Getting Bits Back from Compressed Model ParametersMarton Havasi, Robert Peharz, José Miguel Hernández-Lobato. [doi]
• Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted HardwareFlorian Tramèr, Dan Boneh. [doi]
• Composing Complex Skills by Learning Transition PoliciesYoungwoon Lee, Shao-Hua Sun, Sriram Somasundaram, Edward S. Hu, Joseph J. Lim. [doi]
• Decoupled Weight Decay RegularizationIlya Loshchilov, Frank Hutter. [doi]
• Detecting Egregious Responses in Neural Sequence-to-sequence ModelsTianxing He, James R. Glass. [doi]
• Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale ModelingJosue Nassar, Scott W. Linderman, Mónica F. Bugallo, Il Memming Park. [doi]
• Learning protein sequence embeddings using information from structureTristan Bepler, Bonnie Berger. [doi]
• On the Turing Completeness of Modern Neural Network ArchitecturesJorge Pérez 0001, Javier Marinkovic, Pablo Barceló. [doi]
• Distributional Concavity Regularization for GANsShoichiro Yamaguchi, Masanori Koyama. [doi]
• Overcoming Catastrophic Forgetting for Continual Learning via Model AdaptationWenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao, Jinwen Ma, Dongyan Zhao 0001, Rui Yan. [doi]
• Efficient Lifelong Learning with A-GEMArslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, Mohamed Elhoseiny. [doi]
• Diagnosing and Enhancing VAE ModelsBin Dai, David P. Wipf. [doi]
• Optimistic mirror descent in saddle-point problems: Going the extra (gradient) milePanayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar 0001, Georgios Piliouras. [doi]
• Accelerating Nonconvex Learning via Replica Exchange Langevin diffusionYi Chen, Jinglin Chen, Jing Dong, Jian Peng 0001, Zhaoran Wang. [doi]
• Improving Sequence-to-Sequence Learning via Optimal TransportLiqun Chen, Yizhe Zhang, Ruiyi Zhang, Chenyang Tao, Zhe Gan, Haichao Zhang, Bai Li, Dinghan Shen, Changyou Chen, Lawrence Carin. [doi]
• CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space ModelFlorian Mai, Lukas Galke, Ansgar Scherp. [doi]
• Neural Logic MachinesHonghua Dong, Jiayuan Mao, Tian Lin, Chong Wang, Lihong Li 0001, Denny Zhou. [doi]
• A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and DistillationAkhilesh Gotmare, Nitish Shirish Keskar, Caiming Xiong, Richard Socher. [doi]
• Episodic Curiosity through ReachabilityNikolay Savinov, Anton Raichuk, Damien Vincent, Raphaël Marinier, Marc Pollefeys, Timothy P. Lillicrap, Sylvain Gelly. [doi]
• Are adversarial examples inevitable?Ali Shafahi, W. Ronny Huang, Christoph Studer, Soheil Feizi, Tom Goldstein. [doi]
• Whitening and Coloring Batch Transform for GANsAliaksandr Siarohin, Enver Sangineto, Nicu Sebe. [doi]
• DPSNet: End-to-end Deep Plane Sweep StereoSunghoon Im, Hae-Gon Jeon, Stephen Lin, In-So Kweon. [doi]
• Equi-normalization of Neural NetworksPierre Stock, Benjamin Graham, Rémi Gribonval, Hervé Jégou. [doi]
• A Mean Field Theory of Batch NormalizationGreg Yang, Jeffrey Pennington, Vinay Rao, Jascha Sohl-Dickstein, Samuel S. Schoenholz. [doi]
• Snip: single-Shot Network Pruning based on Connection sensitivityNamhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr. [doi]
• Supervised Community Detection with Line Graph Neural NetworksZhengdao Chen, Lisha Li, Joan Bruna. [doi]
• Variational Bayesian Phylogenetic InferenceCheng Zhang, Frederick A. Matsen IV. [doi]
• Two-Timescale Networks for Nonlinear Value Function ApproximationWesley Chung, Somjit Nath, Ajin Joseph, Martha White. [doi]
• Fixup Initialization: Residual Learning Without NormalizationHongyi Zhang, Yann N. Dauphin, Tengyu Ma. [doi]
• Convolutional Neural Networks on Non-uniform Geometrical Signals Using Euclidean Spectral TransformationChiyu Max Jiang, Dequan Wang, Jingwei Huang, Philip Marcus, Matthias Nießner. [doi]
• Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-MotionRuiQi Gao, Jianwen Xie, Song Chun Zhu, Ying Nian Wu. [doi]
• Variational Autoencoder with Arbitrary ConditioningOleg Ivanov, Michael Figurnov, Dmitry P. Vetrov. [doi]
• The Limitations of Adversarial Training and the Blind-Spot AttackHuan Zhang, Hongge Chen, Zhao Song, Duane S. Boning, Inderjit S. Dhillon, Cho-Jui Hsieh. [doi]
• Theoretical Analysis of Auto Rate-Tuning by Batch NormalizationSanjeev Arora, Zhiyuan Li, Kaifeng Lyu. [doi]
• MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncodersXuezhe Ma, Chunting Zhou, Eduard H. Hovy. [doi]
• Learning Two-layer Neural Networks with Symmetric InputsRong Ge 0001, Rohith Kuditipudi, Zhize Li, Xiang Wang. [doi]
• GamePad: A Learning Environment for Theorem ProvingDaniel Huang 0001, Prafulla Dhariwal, Dawn Song, Ilya Sutskever. [doi]
• Adversarial Imitation via Variational Inverse Reinforcement LearningAhmed H. Qureshi, Byron Boots, Michael C. Yip. [doi]
• Neural Speed Reading with Structural-Jump-LSTMChristian Hansen 0004, Casper Hansen, Stephen Alstrup, Jakob Grue Simonsen, Christina Lioma. [doi]
• Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation LearningIlya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, Sergey Levine, Jonathan Tompson. [doi]
• Mode NormalizationLucas Deecke, Iain Murray 0001, Hakan Bilen. [doi]
• Augmented Cyclic Adversarial Learning for Low Resource Domain AdaptationEhsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong, Richard Socher. [doi]
• Guiding Policies with Language via Meta-LearningJohn D. Co-Reyes, Abhishek Gupta 0004, Suvansh Sanjeev, Nick Altieri, Jacob Andreas, John DeNero, Pieter Abbeel, Sergey Levine. [doi]
• Sample Efficient Adaptive Text-to-SpeechYutian Chen, Yannis M. Assael, Brendan Shillingford, David Budden, Scott E. Reed, Heiga Zen, Quan Wang, Luis C. Cobo, Andrew Trask, Ben Laurie, Çaglar Gülçehre, Aäron Van Den Oord, Oriol Vinyals, Nando de Freitas. [doi]
• Adversarial Reprogramming of Neural NetworksGamaleldin F. Elsayed, Ian J. Goodfellow, Jascha Sohl-Dickstein. [doi]
• Optimal Control Via Neural Networks: A Convex ApproachYize Chen, Yuanyuan Shi, Baosen Zhang. [doi]
• DeepOBS: A Deep Learning Optimizer Benchmark SuiteFrank Schneider, Lukas Balles, Philipp Hennig. [doi]
• h-detach: Modifying the LSTM Gradient Towards Better OptimizationBhargav Kanuparthi, Devansh Arpit, Giancarlo Kerg, Nan Rosemary Ke, Ioannis Mitliagkas, Yoshua Bengio. [doi]
• Near-Optimal Representation Learning for Hierarchical Reinforcement LearningOfir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine. [doi]
• A Kernel Random Matrix-Based Approach for Sparse PCAMohamed-El-Amine Seddik, Mohamed Tamaazousti, Romain Couillet. [doi]
• Unsupervised Speech Recognition via Segmental Empirical Output Distribution MatchingChih-Kuan Yeh, Jianshu Chen, Chengzhu Yu, Dong Yu. [doi]
• DOM-Q-NET: Grounded RL on Structured LanguageSheng Jia, Jamie Kiros, Jimmy Ba. [doi]
• ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary NetworksMingzhang Yin, Mingyuan Zhou. [doi]
• Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticityThomas Miconi, Aditya Rawal, Jeff Clune, Kenneth O. Stanley. [doi]
• Measuring and regularizing networks in function spaceAri S. Benjamin, David Rolnick, Konrad P. Körding. [doi]
• Probabilistic Planning with Sequential Monte Carlo methodsAlexandre Piché, Valentin Thomas, Cyril Ibrahim, Yoshua Bengio, Chris Pal. [doi]
• Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information FlowXue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, Sergey Levine. [doi]
• Discriminator Rejection SamplingSamaneh Azadi, Catherine Olsson, Trevor Darrell, Ian J. Goodfellow, Augustus Odena. [doi]
• Anytime Minibatch: Exploiting Stragglers in Online Distributed OptimizationNuwan S. Ferdinand, Haider Al-Lawati, Stark C. Draper, Matthew S. Nokleby. [doi]
• Defensive Quantization: When Efficiency Meets RobustnessJi Lin, Chuang Gan, Song Han. [doi]
• An Empirical Study of Example Forgetting during Deep Neural Network LearningMariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoffrey J. Gordon. [doi]
• Learning-Based Frequency Estimation AlgorithmsChen-Yu Hsu, Piotr Indyk, Dina Katabi, Ali Vakilian. [doi]
• Deep Convolutional Networks as shallow Gaussian ProcessesAdrià Garriga-Alonso, Carl Edward Rasmussen, Laurence Aitchison. [doi]
• Reward Constrained Policy OptimizationChen Tessler, Daniel J. Mankowitz, Shie Mannor. [doi]
• Functional variational Bayesian Neural NetworksShengyang Sun, Guodong Zhang, Jiaxin Shi, Roger B. Grosse. [doi]
• Beyond Greedy Ranking: Slate Optimization via List-CVAERay Jiang, Sven Gowal, Yuqiu Qian, Timothy A. Mann, Danilo J. Rezende. [doi]
• Hierarchical Generative Modeling for Controllable Speech SynthesisWei-Ning Hsu, Yu Zhang 0033, Ron J. Weiss, Heiga Zen, Yonghui Wu, Yuxuan Wang, Yuan Cao, Ye Jia, Zhifeng Chen, Jonathan Shen, Patrick Nguyen, Ruoming Pang. [doi]
• Bias-Reduced Uncertainty Estimation for Deep Neural ClassifiersYonatan Geifman, Guy Uziel, Ran El-Yaniv. [doi]
• Understanding Straight-Through Estimator in Training Activation Quantized Neural NetsPenghang Yin, Jiancheng Lyu, Shuai Zhang 0009, Stanley J. Osher, Yingyong Qi, Jack Xin. [doi]
• Learning Multimodal Graph-to-Graph Translation for Molecule OptimizationWengong Jin, Kevin Yang, Regina Barzilay, Tommi S. Jaakkola. [doi]
• Variance Networks: When Expectation Does Not Meet Your ExpectationsKirill Neklyudov, Dmitry Molchanov, Arsenii Ashukha, Dmitry P. Vetrov. [doi]
• Learning Programmatically Structured Representations with Perceptor GradientsSvetlin Penkov, Subramanian Ramamoorthy. [doi]
• Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural NetworksJoshua J. Michalenko, Ameesh Shah, Abhinav Verma, Richard G. Baraniuk, Swarat Chaudhuri, Ankit B. Patel. [doi]
• Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based ControlKendall Lowrey, Aravind Rajeswaran, Sham M. Kakade, Emanuel Todorov, Igor Mordatch. [doi]
• Emergent Coordination Through CompetitionSiqi Liu, Guy Lever, Josh Merel, Saran Tunyasuvunakool, Nicolas Heess, Thore Graepel. [doi]
• Universal TransformersMostafa Dehghani 0001, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Lukasz Kaiser. [doi]
• Residual Non-local Attention Networks for Image RestorationYulun Zhang, Kunpeng Li, Kai Li 0012, Bineng Zhong, Yun Fu 0001. [doi]
• Adversarial Attacks on Graph Neural Networks via Meta LearningDaniel Zügner, Stephan Günnemann. [doi]