Table of Contents

• Abstract Diagrammatic Reasoning with Multiplex Graph NetworksDuo Wang, Mateja Jamnik, Pietro Liò. [doi]
• Towards Stable and Efficient Training of Verifiably Robust Neural NetworksHuan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal, Robert Stanforth, Bo Li, Duane S. Boning, Cho-Jui Hsieh. [doi]
• Unpaired Point Cloud Completion on Real Scans using Adversarial TrainingXuelin Chen, Baoquan Chen, Niloy J. Mitra. [doi]
• Sub-policy Adaptation for Hierarchical Reinforcement LearningAlexander C. Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel. [doi]
• Ridge Regression: Structure, Cross-Validation, and SketchingSiFan Liu, Edgar Dobriban. [doi]
• Language GANs Falling ShortMassimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau, Laurent Charlin. [doi]
• Scalable Neural Methods for Reasoning With a Symbolic Knowledge BaseWilliam W. Cohen, Haitian Sun, R. Alex Hofer, Matthew Siegler. [doi]
• The Implicit Bias of Depth: How Incremental Learning Drives GeneralizationDaniel Gissin, Shai Shalev-Shwartz, Amit Daniely. [doi]
• LAMOL: LAnguage MOdeling for Lifelong Language LearningFan-Keng Sun, Cheng-Hao Ho, Hung-yi Lee. [doi]
• State Alignment-based Imitation LearningFangchen Liu, Zhan Ling, Tongzhou Mu, Hao Su. [doi]
• Robust training with ensemble consensusJisoo Lee, Sae-Young Chung. [doi]
• SNODE: Spectral Discretization of Neural ODEs for System IdentificationAlessio Quaglino, Marco Gallieri, Jonathan Masci, Jan Koutník. [doi]
• Tree-Structured Attention with Hierarchical AccumulationXuan-Phi Nguyen, Shafiq Joty, Steven H. C. Hoi, Richard Socher. [doi]
• Learning from Explanations with Neural Execution TreeZiqi Wang, Yujia Qin, Wenxuan Zhou, Jun Yan 0001, Qinyuan Ye, Leonardo Neves, Zhiyuan Liu 0001, Xiang Ren. [doi]
• Thinking While Moving: Deep Reinforcement Learning with Concurrent ControlTed Xiao, Eric Jang, Dmitry Kalashnikov, Sergey Levine, Julian Ibarz, Karol Hausman, Alexander Herzog. [doi]
• Cross-Domain Few-Shot Classification via Learned Feature-Wise TransformationHung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang, Ming-Hsuan Yang 0001. [doi]
• Dynamic Time Lag Regression: Predicting What & WhenMandar Chandorkar, Cyril Furtlehner, Bala Poduval, Enrico Camporeale, Michèle Sebag. [doi]
• Explanation by Progressive ExaggerationSumedha Singla, Brian Pollack, Junxiang Chen, Kayhan Batmanghelich. [doi]
• Data-dependent Gaussian Prior Objective for Language GenerationZuchao Li, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Zhuosheng Zhang 0001, Hai Zhao. [doi]
• Mixed Precision DNNs: All you need is a good parametrizationStefan Uhlich, Lukas Mauch, Fabien Cardinaux, Kazuki Yoshiyama, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura. [doi]
• An Exponential Learning Rate Schedule for Deep LearningZhiyuan Li 0005, Sanjeev Arora. [doi]
• Gap-Aware Mitigation of Gradient StalenessSaar Barkai, Ido Hakimi, Assaf Schuster. [doi]
• Defending Against Physically Realizable Attacks on Image ClassificationTong Wu, Liang Tong, Yevgeniy Vorobeychik. [doi]
• Vid2Game: Controllable Characters Extracted from Real-World VideosOran Gafni, Lior Wolf, Yaniv Taigman. [doi]
• DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity MeasuresHuanrui Yang, Wei Wen, Hai Li. [doi]
• PairNorm: Tackling Oversmoothing in GNNsLingxiao Zhao, Leman Akoglu. [doi]
• Adversarial Lipschitz RegularizationDávid Terjék. [doi]
• Fair Resource Allocation in Federated LearningTian Li, Maziar Sanjabi, Ahmad Beirami, Virginia Smith. [doi]
• Neural Stored-program MemoryHung Le, Truyen Tran 0001, Svetha Venkatesh. [doi]
• Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep LearningArsenii Ashukha, Alexander Lyzhov, Dmitry Molchanov, Dmitry P. Vetrov. [doi]
• A Probabilistic Formulation of Unsupervised Text Style TransferJunxian He, Xinyi Wang, Graham Neubig, Taylor Berg-Kirkpatrick. [doi]
• Target-Embedding Autoencoders for Supervised Representation LearningDaniel Jarrett, Mihaela van der Schaar. [doi]
• State-only Imitation with Transition Dynamics MismatchTanmay Gangwani, Jian Peng 0001. [doi]
• SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and DecompositionZhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, Sungjin Ahn. [doi]
• Learning Robust Representations via Multi-View Information BottleneckMarco Federici, Anjan Dutta 0001, Patrick Forré, Nate Kushman, Zeynep Akata. [doi]
• Recurrent neural circuits for contour detectionDrew Linsley, Junkyung Kim, Alekh Ashok, Thomas Serre. [doi]
• Learning Efficient Parameter Server Synchronization Policies for Distributed SGDRong Zhu, Sheng Yang, Andreas Pfadler, Zhengping Qian, Jingren Zhou. [doi]
• SCALOR: Generative World Models with Scalable Object RepresentationsJindong Jiang, Sepehr Janghorbani, Gerard de Melo, Sungjin Ahn. [doi]
• Detecting Extrapolation with Local EnsemblesDavid Madras, James Atwood, Alexander D'Amour. [doi]
• Progressive Learning and Disentanglement of Hierarchical RepresentationsZhiyuan Li 0007, Jaideep Vitthal Murkute, Prashnna Kumar Gyawali, Linwei Wang. [doi]
• Accelerating SGD with momentum for over-parameterized learningChaoyue Liu, Mikhail Belkin. [doi]
• A Theoretical Analysis of the Number of Shots in Few-Shot LearningTianshi Cao, Marc T. Law, Sanja Fidler. [doi]
• Restricting the Flow: Information Bottlenecks for AttributionKarl Schulz, Leon Sixt, Federico Tombari, Tim Landgraf. [doi]
• White Noise Analysis of Neural NetworksAli Borji, Sikun Lin. [doi]
• Piecewise linear activations substantially shape the loss surfaces of neural networksFengxiang He, Bohan Wang, Dacheng Tao. [doi]
• NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading ComprehensionSeohyun Back, Sai Chetan Chinthakindi, Akhil Kedia, Haejun Lee, Jaegul Choo. [doi]
• A Fair Comparison of Graph Neural Networks for Graph ClassificationFederico Errica, Marco Podda, Davide Bacciu, Alessio Micheli. [doi]
• Massively Multilingual Sparse Word RepresentationsGábor Berend. [doi]
• Don't Use Large Mini-batches, Use Local SGDTao Lin, Sebastian U. Stich, Kumar Kshitij Patel, Martin Jaggi. [doi]
• Doubly Robust Bias Reduction in Infinite Horizon Off-Policy EstimationZiyang Tang, Yihao Feng, Lihong Li 0001, Dengyong Zhou, Qiang Liu. [doi]
• In Search for a SAT-friendly Binarized Neural Network ArchitectureNina Narodytska, Hongce Zhang, Aarti Gupta, Toby Walsh. [doi]
• Ranking Policy GradientKaixiang Lin, Jiayu Zhou. [doi]
• AssembleNet: Searching for Multi-Stream Neural Connectivity in Video ArchitecturesMichael S. Ryoo, A. J. Piergiovanni, Mingxing Tan, Anelia Angelova. [doi]
• Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer MarginColin Wei, Tengyu Ma. [doi]
• Neural tangent kernels, transportation mappings, and universal approximationZiwei Ji, Matus Telgarsky, Ruicheng Xian. [doi]
• A closer look at the approximation capabilities of neural networksKai Fong Ernest Chong. [doi]
• On Computation and Generalization of Generative Adversarial Imitation LearningMinshuo Chen, Yizhou Wang, Tianyi Liu, Zhuoran Yang, Xingguo Li, Zhaoran Wang, Tuo Zhao. [doi]
• Generative Models for Effective ML on Private, Decentralized DatasetsSean Augenstein, H. Brendan McMahan, Daniel Ramage, Swaroop Ramaswamy, Peter Kairouz, Mingqing Chen, Rajiv Mathews, Blaise Agüera y Arcas. [doi]
• Deep Batch Active Learning by Diverse, Uncertain Gradient Lower BoundsJordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford 0001, Alekh Agarwal. [doi]
• The Ingredients of Real World Robotic Reinforcement LearningHenry Zhu, Justin Yu, Abhishek Gupta 0004, Dhruv Shah, Kristian Hartikainen, Avi Singh, Vikash Kumar, Sergey Levine. [doi]
• Imitation Learning via Off-Policy Distribution MatchingIlya Kostrikov, Ofir Nachum, Jonathan Tompson. [doi]
• On the Global Convergence of Training Deep Linear ResNetsDifan Zou, Philip M. Long, Quanquan Gu. [doi]
• Understanding and Robustifying Differentiable Architecture SearchArber Zela, Thomas Elsken, Tonmoy Saikia, Yassine Marrakchi, Thomas Brox, Frank Hutter. [doi]
• Evaluating The Search Phase of Neural Architecture SearchKaicheng Yu, Christian Sciuto, Martin Jaggi, Claudiu Musat, Mathieu Salzmann. [doi]
• ES-MAML: Simple Hessian-Free Meta LearningXingyou Song, Wenbo Gao, Yuxiang Yang, Krzysztof Choromanski, Aldo Pacchiano, Yunhao Tang. [doi]
• Adversarially Robust Representations with Smooth EncodersTaylan Cemgil, Sumedh Ghaisas, Krishnamurthy (Dj) Dvijotham, Pushmeet Kohli. [doi]
• Structured Object-Aware Physics Prediction for Video Modeling and PlanningJannik Kossen, Karl Stelzner, Marcel Hussing, Claas Voelcker, Kristian Kersting. [doi]
• Automated Relational Meta-learningHuaxiu Yao, Xian Wu, Zhiqiang Tao, Yaliang Li, Bolin Ding, Ruirui Li, Zhenhui Li. [doi]
• Adaptive Structural Fingerprints for Graph Attention NetworksKai Zhang 0001, Yaokang Zhu, Jun Wang, Jie Zhang. [doi]
• Deformable Kernels: Adapting Effective Receptive Fields for Object DeformationHang Gao, Xizhou Zhu, Stephen Lin, Jifeng Dai. [doi]
• How much Position Information Do Convolutional Neural Networks Encode?Md. Amirul Islam, Sen Jia, Neil D. B. Bruce. [doi]
• Stochastic Conditional Generative Networks with Basis DecompositionZe Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu. [doi]
• Composing Task-Agnostic Policies with Deep Reinforcement LearningAhmed H. Qureshi, Jacob J. Johnson, Yuzhe Qin, Taylor Henderson, Byron Boots, Michael C. Yip. [doi]
• Self-Adversarial Learning with Comparative Discrimination for Text GenerationWangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou 0001. [doi]
• word2ket: Space-efficient Word Embeddings inspired by Quantum EntanglementAliakbar Panahi, Seyran Saeedi, Tomasz Arodz. [doi]
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution TasksHaebeom Lee, Hayeon Lee, Donghyun Na, Saehoon Kim, Minseop Park, Eunho Yang, Sung Ju Hwang. [doi]
• Prediction Poisoning: Towards Defenses Against DNN Model Stealing AttacksTribhuvanesh Orekondy, Bernt Schiele, Mario Fritz. [doi]
• DDSP: Differentiable Digital Signal ProcessingJesse H. Engel, Lamtharn Hantrakul, Chenjie Gu, Adam Roberts. [doi]
• Variational Autoencoders for Highly Multivariate Spatial Point Processes IntensitiesBaichuan Yuan, Xiaowei Wang, Jianxin Ma, Chang Zhou, Andrea L. Bertozzi, Hongxia Yang. [doi]
• Deep Semi-Supervised Anomaly DetectionLukas Ruff, Robert A. Vandermeulen, Nico Görnitz, Alexander Binder, Emmanuel Müller, Klaus-Robert Müller, Marius Kloft. [doi]
• On the Relationship between Self-Attention and Convolutional LayersJean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi. [doi]
• Dream to Control: Learning Behaviors by Latent ImaginationDanijar Hafner, Timothy P. Lillicrap, Jimmy Ba, Mohammad Norouzi 0002. [doi]
• Network DeconvolutionChengxi Ye, Matthew Evanusa, Hua He, Anton Mitrokhin, Tom Goldstein, James A. Yorke, Cornelia Fermüller, Yiannis Aloimonos. [doi]
• Decoupling Representation and Classifier for Long-Tailed RecognitionBingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, Yannis Kalantidis. [doi]
• CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement LearningJiachen Yang, Alireza Nakhaei, David Isele, Kikuo Fujimura, Hongyuan Zha. [doi]
• Compositional languages emerge in a neural iterated learning modelYi Ren, Shangmin Guo, Matthieu Labeau, Shay B. Cohen, Simon Kirby. [doi]
• Understanding Architectures Learnt by Cell-based Neural Architecture SearchYao Shu, Wei Wang 0059, Shaofeng Cai. [doi]
• PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture SearchYuhui Xu, Lingxi Xie, Xiaopeng Zhang 0008, Xin Chen, Guo-Jun Qi, Qi Tian 0001, Hongkai Xiong. [doi]
• A Baseline for Few-Shot Image ClassificationGuneet Singh Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto. [doi]
• Optimistic Exploration even with a Pessimistic InitialisationTabish Rashid, Bei Peng, Wendelin Boehmer, Shimon Whiteson. [doi]
• Spike-based causal inference for weight alignmentJordan Guerguiev, Konrad P. Körding, Blake A. Richards. [doi]
• Model-based reinforcement learning for biological sequence designChristof Angermüller, David Dohan, David Belanger, Ramya Deshpande, Kevin Murphy, Lucy Colwell. [doi]
• Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley TransformJun Li, Fuxin Li, Sinisa Todorovic. [doi]
• Comparing Rewinding and Fine-tuning in Neural Network PruningAlex Renda, Jonathan Frankle, Michael Carbin. [doi]
• Enhancing Adversarial Defense by k-Winners-Take-AllChang Xiao, Peilin Zhong, Changxi Zheng. [doi]
• Improving Adversarial Robustness Requires Revisiting Misclassified ExamplesYisen Wang 0001, Difan Zou, Jinfeng Yi, James Bailey 0001, Xingjun Ma, Quanquan Gu. [doi]
• BlockSwap: Fisher-guided Block Substitution for Network Compression on a BudgetJack Turner, Elliot J. Crowley, Michael O'Boyle, Amos J. Storkey, Gavin Gray. [doi]
• On Universal Equivariant Set NetworksNimrod Segol, Yaron Lipman. [doi]
• Empirical Studies on the Properties of Linear Regions in Deep Neural NetworksXiao Zhang, Dongrui Wu. [doi]
• Graph Convolutional Reinforcement LearningJiechuan Jiang, Chen Dun, Tiejun Huang, Zongqing Lu. [doi]
• Episodic Reinforcement Learning with Associative MemoryGuangxiang Zhu, Zichuan Lin, Guangwen Yang, Chongjie Zhang. [doi]
• Learning to Plan in High Dimensions via Neural Exploration-Exploitation TreesBinghong Chen, Bo Dai, Qinjie Lin, Guo Ye, Han Liu, Le Song. [doi]
• ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningWeihao Yu, Zihang Jiang, Yanfei Dong, Jiashi Feng. [doi]
• Bridging Mode Connectivity in Loss Landscapes and Adversarial RobustnessPu Zhao, Pin-Yu Chen, Payel Das, Karthikeyan Natesan Ramamurthy, Xue Lin. [doi]
• Learning to solve the credit assignment problemBenjamin James Lansdell, Prashanth Ravi Prakash, Konrad Paul Körding. [doi]
• GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph EmbeddingChenhui Deng, Zhiqiang Zhao, Yongyu Wang, Zhiru Zhang, Zhuo Feng. [doi]
• Learning Disentangled Representations for CounterFactual RegressionNegar Hassanpour, Russell Greiner. [doi]
• A Stochastic Derivative Free Optimization Method with MomentumEduard A. Gorbunov, Adel Bibi, Ozan Sener, El Houcine Bergou, Peter Richtárik. [doi]
• Linear Symmetric Quantization of Neural Networks for Low-precision Integer HardwareXiandong Zhao, Ying Wang, Xuyi Cai, Cheng Liu, Lei Zhang. [doi]
• Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization GuaranteeWei Hu, Zhiyuan Li 0005, Dingli Yu. [doi]
• Intrinsic Motivation for Encouraging Synergistic BehaviorRohan Chitnis, Shubham Tulsiani, Saurabh Gupta 0001, Abhinav Gupta 0001. [doi]
• Sparse Coding with Gated Learned ISTAKailun Wu, Yiwen Guo, Ziang Li, Changshui Zhang. [doi]
• Deep Network Classification by Scattering and Homotopy Dictionary LearningJohn Zarka, Louis Thiry, Tomás Angles, Stéphane Mallat. [doi]
• Understanding the Limitations of Conditional Generative ModelsEthan Fetaya, Jörn-Henrik Jacobsen, Will Grathwohl, Richard S. Zemel. [doi]
• Spectral Embedding of Regularized Block ModelsNathan de Lara, Thomas Bonald. [doi]
• VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-LearningLuisa M. Zintgraf, Kyriacos Shiarlis, Maximilian Igl, Sebastian Schulze, Yarin Gal, Katja Hofmann, Shimon Whiteson. [doi]
• Multi-Scale Representation Learning for Spatial Feature Distributions using Grid CellsGengchen Mai, Krzysztof Janowicz, Bo Yan 0003, Rui Zhu, Ling Cai, Ni Lao. [doi]
• Intensity-Free Learning of Temporal Point ProcessesOleksandr Shchur, Marin Bilos, Stephan Günnemann. [doi]
• Learning representations for binary-classification without backpropagationMathias Lechner. [doi]
• Fantastic Generalization Measures and Where to Find ThemYiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio. [doi]
• Kernelized Wasserstein Natural GradientMichael Arbel, Arthur Gretton, Wuchen Li, Guido Montúfar. [doi]
• The Break-Even Point on Optimization Trajectories of Deep Neural NetworksStanislaw Jastrzebski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, KyungHyun Cho, Krzysztof Geras. [doi]
• Differentially Private Meta-LearningJeffrey Li, Mikhail Khodak, Sebastian Caldas, Ameet Talwalkar. [doi]
• At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?Niv Giladi, Mor Shpigel Nacson, Elad Hoffer, Daniel Soudry. [doi]
• Four Things Everyone Should Know to Improve Batch NormalizationCecilia Summers, Michael J. Dinneen. [doi]
• Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field GamesZuyue Fu, Zhuoran Yang, Yongxin Chen, Zhaoran Wang. [doi]
• How to 0wn the NAS in Your Spare TimeSanghyun Hong, Michael Davinroy, Yigitcan Kaya, Dana Dachman-Soled, Tudor Dumitras. [doi]
• A Mutual Information Maximization Perspective of Language Representation LearningLingpeng Kong, Cyprien de Masson d'Autume, Lei Yu, Wang Ling, Zihang Dai, Dani Yogatama. [doi]
• What graph neural networks cannot learn: depth vs widthAndreas Loukas. [doi]
• Symplectic ODE-Net: Learning Hamiltonian Dynamics with ControlYaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty. [doi]
• Prediction, Consistency, Curvature: Representation Learning for Locally-Linear ControlNir Levine, Yinlam Chow, Rui Shu, Ang Li, Mohammad Ghavamzadeh, Hung Bui. [doi]
• MEMO: A Deep Network for Flexible Combination of Episodic MemoriesAndrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinícius Flores Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, Charles Blundell. [doi]
• Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified FrameworkZirui Wang, Jiateng Xie, Ruochen Xu, Yiming Yang, Graham Neubig, Jaime G. Carbonell. [doi]
• Learning to Control PDEs with Differentiable PhysicsPhilipp Holl, Nils Thuerey, Vladlen Koltun. [doi]
• Deep Learning For Symbolic MathematicsGuillaume Lample, François Charton. [doi]
• Meta-Learning with Warped Gradient DescentSebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Francesco Visin, Hujun Yin, Raia Hadsell. [doi]
• V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous ControlH. Francis Song, Abbas Abdolmaleki, Jost Tobias Springenberg, Aidan Clark, Hubert Soyer, Jack W. Rae, Seb Noury, Arun Ahuja, Siqi Liu, Dhruva Tirumala, Nicolas Heess, Dan Belov, Martin A. Riedmiller, Matthew M. Botvinick. [doi]
• Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence ModelsXisen Jin, Zhongyu Wei, Junyi Du, Xiangyang Xue, Xiang Ren. [doi]
• Compressive Transformers for Long-Range Sequence ModellingJack W. Rae, Anna Potapenko, Siddhant M. Jayakumar, Chloe Hillier, Timothy P. Lillicrap. [doi]
• Variance Reduction With Sparse GradientsMelih Elibol, Lihua Lei, Michael I. Jordan. [doi]
• Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading ComprehensionXinyun Chen, Chen Liang, Adams Wei Yu, Denny Zhou, Dawn Song, Quoc V. Le. [doi]
• Meta Dropout: Learning to Perturb Latent Features for GeneralizationHaebeom Lee, Taewook Nam, Eunho Yang, Sung Ju Hwang. [doi]
• SVQN: Sequential Variational Soft Q-Learning NetworksShiyu Huang, Hang Su, Jun Zhu, Ting Chen. [doi]
• Quantum Algorithms for Deep Convolutional Neural NetworksIordanis Kerenidis, Jonas Landman, Anupam Prakash. [doi]
• To Relieve Your Headache of Training an MRF, Take AdVILChongxuan Li, Chao Du, Kun Xu, Max Welling, Jun Zhu, Bo Zhang 0010. [doi]
• Single Episode Policy Transfer in Reinforcement LearningJiachen Yang, Brenden K. Petersen, Hongyuan Zha, Daniel Faissol. [doi]
• Lite Transformer with Long-Short Range AttentionZhanghao Wu, Zhijian Liu, Ji Lin, Yujun Lin, Song Han. [doi]
• On the Weaknesses of Reinforcement Learning for Neural Machine TranslationLeshem Choshen, Lior Fox, Zohar Aizenbud, Omri Abend. [doi]
• Deep Imitative Models for Flexible Inference, Planning, and ControlNicholas Rhinehart, Rowan McAllister, Sergey Levine. [doi]
• Reducing Transformer Depth on Demand with Structured DropoutAngela Fan, Edouard Grave, Armand Joulin. [doi]
• Scaling Autoregressive Video ModelsDirk Weissenborn, Oscar Täckström, Jakob Uszkoreit. [doi]
• Hoppity: Learning Graph Transformations to Detect and Fix Bugs in ProgramsElizabeth Dinella, Hanjun Dai, Ziyang Li, Mayur Naik, Le Song, Ke Wang. [doi]
• Sliced Cramer Synaptic Consolidation for Preserving Deeply Learned RepresentationsSoheil Kolouri, Nicholas A. Ketz, Andrea Soltoggio, Praveen K. Pilly. [doi]
• Learn to Explain Efficiently via Neural Logic Inductive LearningYuan Yang, Le Song. [doi]
• Understanding l4-based Dictionary Learning: Interpretation, Stability, and RobustnessYuexiang Zhai, Hermish Mehta, Zhengyuan Zhou, Yi Ma 0001. [doi]
• AdvectiveNet: An Eulerian-Lagrangian Fluidic Reservoir for Point Cloud ProcessingXingzhe He, Helen Lu Cao, Bo Zhu. [doi]
• Disentangling neural mechanisms for perceptual groupingJunkyung Kim, Drew Linsley, Kalpit Thakkar, Thomas Serre. [doi]
• Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few ExamplesEleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, Hugo Larochelle. [doi]
• DivideMix: Learning with Noisy Labels as Semi-supervised LearningJunnan Li, Richard Socher, Steven C. H. Hoi. [doi]
• Improving Generalization in Meta Reinforcement Learning using Learned ObjectivesLouis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber. [doi]
• Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive InferenceTing-Kuei Hu, Tianlong Chen, Haotao Wang, Zhangyang Wang. [doi]
• Multiplicative Interactions and Where to Find ThemSiddhant M. Jayakumar, Wojciech M. Czarnecki, Jacob Menick, Jonathan Schwarz, Jack W. Rae, Simon Osindero, Yee Whye Teh, Tim Harley, Razvan Pascanu. [doi]
• Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar InductionTaeuk Kim, Jihun Choi, Daniel Edmiston, Sang-goo Lee. [doi]
• Distributionally Robust Neural NetworksShiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, Percy Liang. [doi]
• Principled Weight Initialization for HypernetworksOscar Chang, Lampros Flokas, Hod Lipson. [doi]
• Reinforced Genetic Algorithm Learning for Optimizing Computation GraphsAditya Paliwal, Felix Gimeno, Vinod Nair, Yujia Li, Miles Lubin, Pushmeet Kohli, Oriol Vinyals. [doi]
• Inductive Matrix Completion Based on Graph Neural NetworksMuhan Zhang, Yixin Chen. [doi]
• Gradient Descent Maximizes the Margin of Homogeneous Neural NetworksKaifeng Lyu, Jian Li. [doi]
• Selection via Proxy: Efficient Data Selection for Deep LearningCody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia. [doi]
• Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural NetworksYuhang Li, Xin Dong, Wei Wang. [doi]
• Unsupervised Clustering using Pseudo-semi-supervised LearningDivam Gupta, Ramachandran Ramjee, Nipun Kwatra, Muthian Sivathanu. [doi]
• Rényi Fair InferenceSina Baharlouei, Maher Nouiehed, Ahmad Beirami, Meisam Razaviyayn. [doi]
• Convolutional Conditional Neural ProcessesJonathan Gordon 0003, Wessel P. Bruinsma, Andrew Y. K. Foong, James Requeima, Yann Dubois, Richard E. Turner. [doi]
• Learning Space Partitions for Nearest Neighbor SearchYihe Dong, Piotr Indyk, Ilya P. Razenshteyn, Tal Wagner. [doi]
• Uncertainty-guided Continual Learning with Bayesian Neural NetworksSayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell, Marcus Rohrbach. [doi]
• Graph Constrained Reinforcement Learning for Natural Language Action SpacesPrithviraj Ammanabrolu, Matthew J. Hausknecht. [doi]
• Bounds on Over-Parameterization for Guaranteed Existence of Descent Paths in Shallow ReLU NetworksArsalan Sharif-Nassab, Saber Salehkaleybar, S. Jamaloddin Golestani. [doi]
• Why Gradient Clipping Accelerates Training: A Theoretical Justification for AdaptivityJingzhao Zhang, Tianxing He, Suvrit Sra, Ali Jadbabaie. [doi]
• CoPhy: Counterfactual Learning of Physical DynamicsFabien Baradel, Natalia Neverova, Julien Mille, Greg Mori, Christian Wolf 0001. [doi]
• Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete LearningQing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, Zhihui Zhu. [doi]
• MMA Training: Direct Input Space Margin Maximization through Adversarial TrainingGavin Weiguang Ding, Yash Sharma, Kry Yik-Chau Lui, Ruitong Huang. [doi]
• ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut. [doi]
• Geometric Insights into the Convergence of Nonlinear TD LearningDavid Brandfonbrener, Joan Bruna. [doi]
• TabFact: A Large-scale Dataset for Table-based Fact VerificationWenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou, William Yang Wang. [doi]
• Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural NetworksSreyas Mohan, Zahra Kadkhodaie, Eero P. Simoncelli, Carlos Fernandez-Granda. [doi]
• Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear NetworksWei Hu, Lechao Xiao, Jeffrey Pennington. [doi]
• Graph inference learning for semi-supervised classificationChunyan Xu, Zhen Cui, Xiaobin Hong, Tong Zhang, Jian Yang, Wei Liu 0005. [doi]
• Non-Autoregressive Dialog State TrackingHung Le, Richard Socher, Steven C. H. Hoi. [doi]
• Neural Execution of Graph AlgorithmsPetar Velickovic, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell. [doi]
• CAQL: Continuous Action Q-LearningMoonkyung Ryu, Yinlam Chow, Ross Anderson, Christian Tjandraatmadja, Craig Boutilier. [doi]
• Few-Shot Learning on graphs via super-Classes based on Graph spectral MeasuresJatin Chauhan, Deepak Nathani, Manohar Kaul. [doi]
• VideoFlow: A Conditional Flow-Based Model for Stochastic Video GenerationManoj Kumar, Mohammad Babaeizadeh, Dumitru Erhan, Chelsea Finn, Sergey Levine, Laurent Dinh, Durk Kingma. [doi]
• Double Neural Counterfactual Regret MinimizationHui Li, Kailiang Hu, Shaohua Zhang, Yuan Qi, Le Song. [doi]
• Federated Learning with Matched AveragingHongyi Wang, Mikhail Yurochkin, Yuekai Sun, Dimitris S. Papailiopoulos, Yasaman Khazaeni. [doi]
• Understanding and Improving Information Transfer in Multi-Task LearningSen Wu 0002, Hongyang R. Zhang, Christopher Ré. [doi]
• N-BEATS: Neural basis expansion analysis for interpretable time series forecastingBoris N. Oreshkin, Dmitri Carpov, Nicolas Chapados, Yoshua Bengio. [doi]
• BackPACK: Packing more into BackpropFelix Dangel, Frederik Kunstner, Philipp Hennig. [doi]
• Exploration in Reinforcement Learning with Deep Covering OptionsYuu Jinnai, Jee Won Park, Marlos C. Machado, George Dimitri Konidaris. [doi]
• Deep Double Descent: Where Bigger Models and More Data HurtPreetum Nakkiran, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak, Ilya Sutskever. [doi]
• StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingWei Wang 0225, Bin Bi, Ming Yan, Chen Wu, Jiangnan Xia, Zuyi Bao, Liwei Peng, Luo Si. [doi]
• SQIL: Imitation Learning via Reinforcement Learning with Sparse RewardsSiddharth Reddy, Anca D. Dragan, Sergey Levine. [doi]
• Strategies for Pre-training Graph Neural NetworksWeihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay S. Pande, Jure Leskovec. [doi]
• Curriculum Loss: Robust Learning and Generalization against Label CorruptionYueming Lyu, Ivor W. Tsang. [doi]
• Learning-Augmented Data Stream AlgorithmsTanqiu Jiang, Yi Li, Honghao Lin, Yisong Ruan, David P. Woodruff. [doi]
• Budgeted Training: Rethinking Deep Neural Network Training Under Resource ConstraintsMengtian Li, Ersin Yumer, Deva Ramanan. [doi]
• Semi-Supervised Generative Modeling for Controllable Speech SynthesisRaza Habib, Soroosh Mariooryad, Matt Shannon, Eric Battenberg, R. J. Skerry-Ryan, Daisy Stanton, David Kao, Tom Bagby. [doi]
• High Fidelity Speech Synthesis with Adversarial NetworksMikolaj Binkowski, Jeff Donahue, Sander Dieleman, Aidan Clark, Erich Elsen, Norman Casagrande, Luis C. Cobo, Karen Simonyan. [doi]
• Provable Filter Pruning for Efficient Neural NetworksLucas Liebenwein, Cenk Baykal, Harry Lang, Dan Feldman, Daniela Rus. [doi]
• Pruned Graph Scattering TransformsVassilis N. Ioannidis, Siheng Chen, Georgios B. Giannakis. [doi]
• Scalable Model Compression by Entropy Penalized ReparameterizationDeniz Oktay, Johannes Ballé, Saurabh Singh, Abhinav Shrivastava. [doi]
• On Identifiability in TransformersGino Brunner, Yang Liu, Damian Pascual, Oliver Richter, Massimiliano Ciaramita, Roger Wattenhofer. [doi]
• Meta-learning curiosity algorithmsFerran Alet, Martin F. Schneider, Tomás Lozano-Pérez, Leslie Pack Kaelbling. [doi]
• SELF: Learning to Filter Noisy Labels with Self-EnsemblingDuc Tam Nguyen, Chaithanya Kumar Mummadi, Thi-Phuong-Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, Thomas Brox. [doi]
• Neural Tangents: Fast and Easy Infinite Neural Networks in PythonRoman Novak, Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander A. Alemi, Jascha Sohl-Dickstein, Samuel S. Schoenholz. [doi]
• Extreme Tensoring for Low-Memory PreconditioningXinyi Chen, Naman Agarwal, Elad Hazan, Cyril Zhang, Yi Zhang. [doi]
• Image-guided Neural Object RenderingJustus Thies, Michael Zollhöfer, Christian Theobalt, Marc Stamminger, Matthias Nießner. [doi]
• Lipschitz constant estimation of Neural Networks via sparse polynomial optimizationFabian Latorre Gómez, Paul Rolland, Volkan Cevher. [doi]
• Plug and Play Language Models: A Simple Approach to Controlled Text GenerationSumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, Rosanne Liu. [doi]
• Improved memory in recurrent neural networks with sequential non-normal dynamicsEmin Orhan, Xaq Pitkow. [doi]
• Cross-Lingual Ability of Multilingual BERT: An Empirical StudyKarthikeyan K, Zihan Wang, Stephen Mayhew, Dan Roth. [doi]
• Meta-Learning Acquisition Functions for Transfer Learning in Bayesian OptimizationMichael Volpp, Lukas P. Fröhlich, Kirsten Fischer, Andreas Doerr, Stefan Falkner, Frank Hutter, Christian Daniel. [doi]
• IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target NetworksMichael Luo, Jiahao Yao, Richard Liaw, Eric Liang, Ion Stoica. [doi]
• Phase Transitions for the Information Bottleneck in Representation LearningTailin Wu, Ian Fischer. [doi]
• Self-Supervised Learning of Appliance UsageChen-Yu Hsu 0001, Abbas Zeitoun, Guang-He Lee, Dina Katabi, Tommi S. Jaakkola. [doi]
• Physics-aware Difference Graph Networks for Sparsely-Observed DynamicsSungyong Seo, Chuizheng Meng, Yan Liu. [doi]
• Learning to LinkMaria-Florina Balcan, Travis Dick, Manuel Lang. [doi]
• Dynamics-Aware Unsupervised Discovery of SkillsArchit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar, Karol Hausman. [doi]
• Learning Expensive Coordination: An Event-Based Deep RL ApproachZhenyu Shi, Runsheng Yu, Xinrun Wang, Rundong Wang, Youzhi Zhang, Hanjiang Lai, Bo An 0001. [doi]
• Are Transformers universal approximators of sequence-to-sequence functions?Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar. [doi]
• AutoQ: Automated Kernel-Wise Neural Network QuantizationQian Lou, Feng Guo, Minje Kim, Lantao Liu, Lei Jiang.. [doi]
• GenDICE: Generalized Offline Estimation of Stationary ValuesRuiyi Zhang, Bo Dai, Lihong Li 0001, Dale Schuurmans. [doi]
• Neural Network Branching for Neural Network VerificationJingyue Lu, M. Pawan Kumar. [doi]
• Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing SystemsChris Reinke, Mayalen Etcheverry, Pierre-Yves Oudeyer. [doi]
• AMRL: Aggregated Memory For Reinforcement LearningJacob Beck, Kamil Ciosek, Sam Devlin, Sebastian Tschiatschek, Cheng Zhang, Katja Hofmann. [doi]
• Domain Adaptive Multibranch NetworksRóger Bermúdez-Chacón, Mathieu Salzmann, Pascal Fua. [doi]
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent RepresentationsMartin Engelcke, Adam R. Kosiorek, Oiwi Parker Jones, Ingmar Posner. [doi]
• MACER: Attack-free and Scalable Robust Training via Maximizing Certified RadiusRuntian Zhai, Chen Dan, Di He, Huan Zhang, Boqing Gong, Pradeep Ravikumar, Cho-Jui Hsieh, Liwei Wang 0001. [doi]
• Escaping Saddle Points Faster with Stochastic MomentumJun-Kun Wang, Chi-Heng Lin, Jacob D. Abernethy. [doi]
• Understanding Why Neural Networks Generalize Well Through GSNR of ParametersJinlong Liu, Yunzhi Bai, Guoqing Jiang, Ting Chen, Huayan Wang. [doi]
• Variational Hetero-Encoder Randomized GANs for Joint Image-Text ModelingHao Zhang 0050, Bo Chen, Long Tian, Zhengjue Wang, Mingyuan Zhou. [doi]
• Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box EmbeddingsHongyu Ren, Weihua Hu, Jure Leskovec. [doi]
• Incorporating BERT into Neural Machine TranslationJinhua Zhu, Yingce Xia, Lijun Wu, Di He, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu. [doi]
• Quantifying the Cost of Reliable Photo Authentication via High-Performance Learned Lossy RepresentationsPawel Korus, Nasir D. Memon. [doi]
• Gradientless Descent: High-Dimensional Zeroth-Order OptimizationDaniel Golovin, John Karro, Greg Kochanski, Chansoo Lee, Xingyou Song, Qiuyi Zhang. [doi]
• Thieves on Sesame Street! Model Extraction of BERT-based APIsKalpesh Krishna, Gaurav Singh Tomar, Ankur P. Parikh, Nicolas Papernot, Mohit Iyyer. [doi]
• Understanding Generalization in Recurrent Neural NetworksZhuozhuo Tu, Fengxiang He, Dacheng Tao. [doi]
• Understanding Knowledge Distillation in Non-autoregressive Machine TranslationChunting Zhou, Jiatao Gu, Graham Neubig. [doi]
• Variational Recurrent Models for Solving Partially Observable Control TasksDongqi Han, Kenji Doya, Jun Tani. [doi]
• CLN2INV: Learning Loop Invariants with Continuous Logic NetworksGabriel Ryan, Justin Wong, Jianan Yao, Ronghui Gu, Suman Jana. [doi]
• Cyclical Stochastic Gradient MCMC for Bayesian Deep LearningRuqi Zhang, Chunyuan Li, Jianyi Zhang, Changyou Chen, Andrew Gordon Wilson. [doi]
• Unsupervised Model Selection for Variational Disentangled Representation LearningSunny Duan, Loic Matthey, Andre Saraiva, Nick Watters, Christopher Burgess, Alexander Lerchner, Irina Higgins. [doi]
• Identifying through Flows for Recovering Latent RepresentationsShen Li, Bryan Hooi, Gim Hee Lee. [doi]
• Adversarially robust transfer learningAli Shafahi, Parsa Saadatpanah, Chen Zhu, Amin Ghiasi, Christoph Studer, David W. Jacobs, Tom Goldstein. [doi]
• RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image SynthesisAtsuhiro Noguchi, Tatsuya Harada. [doi]
• Convergence of Gradient Methods on Bilinear Zero-Sum GamesGuojun Zhang, Yaoliang Yu. [doi]
• Denoising and Regularization via Exploiting the Structural Bias of Convolutional GeneratorsReinhard Heckel, Mahdi Soltanolkotabi. [doi]
• The Logical Expressiveness of Graph Neural NetworksPablo Barceló, Egor V. Kostylev, Mikaël Monet, Jorge Pérez 0001, Juan L. Reutter, Juan Pablo Silva. [doi]
• Progressive Memory Banks for Incremental Domain AdaptationNabiha Asghar, Lili Mou, Kira A. Selby, Kevin D. Pantasdo, Pascal Poupart, Xin Jiang. [doi]
• On Robustness of Neural Ordinary Differential EquationsHanshu Yan, Jiawei Du, Vincent Tan, Jiashi Feng. [doi]
• Neural Policy Gradient Methods: Global Optimality and Rates of ConvergenceLingxiao Wang, Qi Cai, Zhuoran Yang, Zhaoran Wang. [doi]
• You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph EmbeddingsDaniel Ruffinelli, Samuel Broscheit, Rainer Gemulla. [doi]
• Option Discovery using Deep Skill ChainingAkhil Bagaria, George Konidaris. [doi]
• Network Randomization: A Simple Technique for Generalization in Deep Reinforcement LearningKimin Lee, Kibok Lee, Jinwoo Shin, Honglak Lee. [doi]
• Unrestricted Adversarial Examples via Semantic ManipulationAnand Bhattad, Min Jin Chong, Kaizhao Liang, Bo Li, David A. Forsyth. [doi]
• Projection-Based Constrained Policy OptimizationTsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge. [doi]
• The asymptotic spectrum of the Hessian of DNN throughout trainingArthur Jacot, Franck Gabriel, Clément Hongler. [doi]
• An Inductive Bias for Distances: Neural Nets that Respect the Triangle InequalitySilviu Pitis, Harris Chan, Kiarash Jamali, Jimmy Ba. [doi]
• Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object TrackingYunhan Jia, Yantao Lu, Junjie Shen, Qi Alfred Chen, Hao Chen, Zhenyu Zhong, Tao Wei. [doi]
• Adaptive Correlated Monte Carlo for Contextual Categorical Sequence GenerationXinjie Fan, Yizhe Zhang, Zhendong Wang, Mingyuan Zhou. [doi]
• BayesOpt Adversarial AttackBinxin Ru, Adam D. Cobb, Arno Blaas, Yarin Gal. [doi]
• EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness Against Adversarial AttacksSanchari Sen, Balaraman Ravindran, Anand Raghunathan. [doi]
• Gradient-Based Neural DAG LearningSébastien Lachapelle, Philippe Brouillard, Tristan Deleu, Simon Lacoste-Julien. [doi]
• Harnessing Structures for Value-Based Planning and Reinforcement LearningYuzhe Yang, Guo Zhang, Zhi Xu, Dina Katabi. [doi]
• Robust Local Features for Improving the Generalization of Adversarial TrainingChuanbiao Song, Kun He 0001, Jiadong Lin, Liwei Wang 0001, John E. Hopcroft. [doi]
• From Variational to Deterministic AutoencodersPartha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael J. Black, Bernhard Schölkopf. [doi]
• And the Bit Goes Down: Revisiting the Quantization of Neural NetworksPierre Stock, Armand Joulin, Rémi Gribonval, Benjamin Graham, Hervé Jégou. [doi]
• Lookahead: A Far-sighted Alternative of Magnitude-based PruningSejun Park, Jaeho Lee, Sangwoo Mo, Jinwoo Shin. [doi]
• Hyper-SAGNN: a self-attention based graph neural network for hypergraphsRuochi Zhang, Yuesong Zou, Jian Ma 0004. [doi]
• Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networksZiwei Ji, Matus Telgarsky. [doi]
• Measuring the Reliability of Reinforcement Learning AlgorithmsStephanie C. Y. Chan, Samuel Fishman, Anoop Korattikara, John Canny, Sergio Guadarrama. [doi]
• A Closer Look at the Optimization Landscapes of Generative Adversarial NetworksHugo Berard, Gauthier Gidel, Amjad Almahairi, Pascal Vincent, Simon Lacoste-Julien. [doi]
• Posterior sampling for multi-agent reinforcement learning: solving extensive games with imperfect informationYichi Zhou, Jialian Li, Jun Zhu. [doi]
• Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen CategoriesTiange Luo, Kaichun Mo, Zhiao Huang, Jiarui Xu, Siyu Hu, Liwei Wang 0001, Hao Su. [doi]
• V4D: 4D Convolutional Neural Networks for Video-level Representation LearningShiwen Zhang, Sheng Guo, Weilin Huang, Matthew R. Scott, Limin Wang 0002. [doi]
• Adversarial Training and Provable Defenses: Bridging the GapMislav Balunovic, Martin T. Vechev. [doi]
• U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image TranslationJunho Kim, Minjae Kim, Hyeonwoo Kang, KwangHee Lee. [doi]
• Input Complexity and Out-of-distribution Detection with Likelihood-based Generative ModelsJoan Serrà, David Álvarez, Vicenç Gómez, Olga Slizovskaia, José F. Núñez, Jordi Luque. [doi]
• SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable ModelsYucen Luo, Alex Beatson, Mohammad Norouzi 0002, Jun Zhu 0001, David Duvenaud, Ryan P. Adams, Ricky T. Q. Chen. [doi]
• Efficient and Information-Preserving Future Frame Prediction and BeyondWei Yu, Yichao Lu, Steve Easterbrook, Sanja Fidler. [doi]
• Order Learning and Its Application to Age EstimationKyungsun Lim, Nyeong-Ho Shin, Young-Yoon Lee, Chang-Su Kim. [doi]
• Neural Arithmetic UnitsAndreas Madsen, Alexander Rosenberg Johansen. [doi]
• Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence ScoringSamuel Humeau, Kurt Shuster, Marie-Anne Lachaux, Jason Weston. [doi]
• Mirror-Generative Neural Machine TranslationZaixiang Zheng, Hao Zhou 0012, Shujian Huang, Lei Li 0018, Xin-Yu Dai, Jiajun Chen. [doi]
• Meta-Learning without MemorizationMingzhang Yin, George Tucker, Mingyuan Zhou, Sergey Levine, Chelsea Finn. [doi]
• Computation Reallocation for Object DetectionFeng Liang, Chen Lin, Ronghao Guo, Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang. [doi]
• Permutation Equivariant Models for Compositional Generalization in LanguageJonathan Gordon 0003, David Lopez-Paz, Marco Baroni, Diane Bouchacourt. [doi]
• FreeLB: Enhanced Adversarial Training for Natural Language UnderstandingChen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, Jingjing Liu. [doi]
• Higher-Order Function Networks for Learning Composable 3D Object RepresentationsEric Mitchell, Selim Engin, Volkan Isler, Daniel D. Lee. [doi]
• Estimating Gradients for Discrete Random Variables by Sampling without ReplacementWouter Kool 0001, Herke van Hoof, Max Welling. [doi]
• Adversarial AutoAugmentXinyu Zhang, Qiang Wang, Jian Zhang, Zhao Zhong. [doi]
• Infinite-Horizon Differentiable Model Predictive ControlSebastian East, Marco Gallieri, Jonathan Masci, Jan Koutník, Mark Cannon. [doi]
• Neural Epitome Search for Architecture-Agnostic Network CompressionDaquan Zhou, Xiaojie Jin, Qibin Hou, Kaixin Wang, Jianchao Yang, Jiashi Feng. [doi]
• Towards Fast Adaptation of Neural Architectures with Meta LearningDongze Lian, Yin Zheng, Yintao Xu, Yanxiong Lu, Leyu Lin, Peilin Zhao, JunZhou Huang, Shenghua Gao. [doi]
• Knowledge Consistency between Neural Networks and BeyondRuofan Liang, Tianlin Li, Longfei Li, Jing Wang, Quanshi Zhang. [doi]
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question GenerationYu Chen 0022, Lingfei Wu, Mohammed J. Zaki. [doi]
• Breaking Certified Defenses: Semantic Adversarial Examples with Spoofed robustness CertificatesAmin Ghiasi, Ali Shafahi, Tom Goldstein. [doi]
• Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear MapsTri Dao, Nimit Sharad Sohoni, Albert Gu, Matthew Eichhorn, Amit Blonder, Megan Leszczynski, Atri Rudra, Christopher Ré. [doi]
• SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with SpikesJohannes C. Thiele, Olivier Bichler, Antoine Dupret. [doi]
• Learning to Represent Programs with Property SignaturesAugustus Odena, Charles Sutton. [doi]
• Understanding the Limitations of Variational Mutual Information EstimatorsJiaming Song, Stefano Ermon. [doi]
• Theory and Evaluation Metrics for Learning Disentangled RepresentationsKien Do, Truyen Tran 0001. [doi]
• Optimal Strategies Against Generative AttacksRoy Mor, Erez Peterfreund, Matan Gavish, Amir Globerson. [doi]
• Fast Task Inference with Variational Intrinsic Successor FeaturesSteven Hansen, Will Dabney, André Barreto, David Warde-Farley, Tom Van de Wiele, Volodymyr Mnih. [doi]
• Behaviour Suite for Reinforcement LearningIan Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener, Andre Saraiva, Katrina McKinney, Tor Lattimore, Csaba Szepesvári, Satinder Singh, Benjamin Van Roy, Richard S. Sutton, David Silver, Hado van Hasselt. [doi]
• Logic and the 2-Simplicial TransformerJames Clift, Dmitry Doryn, Daniel Murfet, James Wallbridge. [doi]
• You Only Train Once: Loss-Conditional Training of Deep NetworksAlexey Dosovitskiy, Josip Djolonga. [doi]
• On the Equivalence between Positional Node Embeddings and Structural Graph RepresentationsBalasubramaniam Srinivasan, Bruno Ribeiro 0001. [doi]
• Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule ReconstructionsYao Qin, Nicholas Frosst, Sara Sabour, Colin Raffel, Garrison W. Cottrell, Geoffrey E. Hinton. [doi]
• Few-shot Text Classification with Distributional SignaturesYujia Bao, Menghua Wu, Shiyu Chang, Regina Barzilay. [doi]
• Controlling generative models with continuous factors of variationsAntoine Plumerault, Hervé Le Borgne, Céline Hudelot. [doi]
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph GenerationChence Shi, Minkai Xu, Zhaocheng Zhu, Weinan Zhang 0001, Ming Zhang 0004, Jian Tang. [doi]
• Meta-Q-LearningRasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola. [doi]
• Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent Variable ModelsYixuan Qiu, Lingsong Zhang, Xiao Wang. [doi]
• Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?Simon S. Du, Sham M. Kakade, Ruosong Wang, Lin F. Yang. [doi]
• Span Recovery for Deep Neural Networks with Applications to Input ObfuscationRajesh Jayaram, David P. Woodruff, Qiuyi Zhang. [doi]
• Rotation-invariant clustering of neuronal responses in primary visual cortexIvan Ustyuzhaninov, Santiago A. Cadena, Emmanouil Froudarakis, Paul G. Fahey, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Fabian H. Sinz, Andreas S. Tolias, Matthias Bethge, Alexander S. Ecker. [doi]
• Causal Discovery with Reinforcement LearningShengyu Zhu, Ignavier Ng, Zhitang Chen. [doi]
• Interpretable Complex-Valued Neural Networks for Privacy ProtectionLiyao Xiang, Hao Zhang, Haotian Ma, Yifan Zhang, Jie Ren, Quanshi Zhang. [doi]
• Batch-shaping for learning conditional channel gated networksBabak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling. [doi]
• Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language ModelWenhan Xiong, Jingfei Du, William Yang Wang, Veselin Stoyanov. [doi]
• Generalization through Memorization: Nearest Neighbor Language ModelsUrvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, Mike Lewis. [doi]
• Once-for-All: Train One Network and Specialize it for Efficient DeploymentHan Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, Song Han. [doi]
• Rethinking Softmax Cross-Entropy Loss for Adversarial RobustnessTianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen 0002, Jun Zhu. [doi]
• Building Deep Equivariant Capsule NetworksSai Raam Venkataraman, S. Balasubramanian, R. Raghunatha Sarma. [doi]
• Transformer-XH: Multi-Evidence Reasoning with eXtra Hop AttentionChen Zhao, Chenyan Xiong, Corby Rosset, Xia Song, Paul N. Bennett, Saurabh Tiwary. [doi]
• Inductive and Unsupervised Representation Learning on Graph Structured ObjectsLichen Wang, Bo Zong, Qianqian Ma, Wei Cheng, Jingchao Ni, Wenchao Yu, Yanchi Liu, Dongjin Song, Haifeng Chen, Yun Fu 0001. [doi]
• Mathematical Reasoning in Latent SpaceDennis Lee, Christian Szegedy, Markus N. Rabe, Sarah M. Loos, Kshitij Bansal. [doi]
• Guiding Program Synthesis by Learning to Generate ExamplesLarissa Laich, Pavol Bielik, Martin T. Vechev. [doi]
• Conservative Uncertainty Estimation By Fitting Prior NetworksKamil Ciosek, Vincent Fortuin, Ryota Tomioka, Katja Hofmann, Richard Turner. [doi]
• Neural Machine Translation with Universal Visual RepresentationZhuosheng Zhang 0001, Kehai Chen, Rui Wang 0015, Masao Utiyama, Eiichiro Sumita, Zuchao Li, Hai Zhao. [doi]
• What Can Neural Networks Reason About?Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka. [doi]
• A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate CaseGreg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro. [doi]
• Regularizing activations in neural networks via distribution matching with the Wasserstein metricTaejong Joo, Donggu Kang, Byunghoon Kim. [doi]
• A Theory of Usable Information under Computational ConstraintsYilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon. [doi]
• Identity Crisis: Memorization and Generalization Under Extreme OverparameterizationChiyuan Zhang, Samy Bengio, Moritz Hardt, Michael C. Mozer, Yoram Singer. [doi]
• RaCT: Toward Amortized Ranking-Critical Training For Collaborative FilteringSam Lobel, Chunyuan Li, Jianfeng Gao, Lawrence Carin. [doi]
• Improving Neural Language Generation with Spectrum ControlLingxiao Wang, Jing Huang 0019, Kevin Huang, Ziniu Hu, Guangtao Wang, Quanquan Gu. [doi]
• Minimizing FLOPs to Learn Efficient Sparse RepresentationsBiswajit Paria, Chih-Kuan Yeh, Ian En-Hsu Yen, Ning Xu, Pradeep Ravikumar, Barnabás Póczos. [doi]
• Differentiable Reasoning over a Virtual Knowledge BaseBhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov, William W. Cohen. [doi]
• Measuring Compositional Generalization: A Comprehensive Method on Realistic DataDaniel Keysers, Nathanael Schärli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, Dmitry Tsarkov, Xiao Wang, Marc van Zee, Olivier Bousquet. [doi]
• Multi-agent Reinforcement Learning for Networked System ControlTianshu Chu, Sandeep Chinchali, Sachin Katti. [doi]
• Learning to Move with Affordance MapsWilliam Qi, Ravi Teja Mullapudi, Saurabh Gupta, Deva Ramanan. [doi]
• Simplified Action Decoder for Deep Multi-Agent Reinforcement LearningHengyuan Hu, Jakob N. Foerster. [doi]
• Influence-Based Multi-Agent ExplorationTonghan Wang 0001, Jianhao Wang, Yi Wu, Chongjie Zhang. [doi]
• Classification-Based Anomaly Detection for General DataLiron Bergman, Yedid Hoshen. [doi]
• Revisiting Self-Training for Neural Sequence GenerationJunxian He, Jiatao Gu, Jiajun Shen, Marc'Aurelio Ranzato. [doi]
• Sample Efficient Policy Gradient Methods with Recursive Variance ReductionPan Xu 0002, Felicia Gao, Quanquan Gu. [doi]
• Weakly Supervised Clustering by Exploiting Unique Class CountMustafa Umit Oner, Hwee Kuan Lee, Wing-Kin Sung. [doi]
• Transferring Optimality Across Data Distributions via Homotopy MethodsMatilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh, Moritz Diehl, Frank Hutter. [doi]
• Mixed-curvature Variational AutoencodersOndrej Skopek, Octavian-Eugen Ganea, Gary Bécigneul. [doi]
• Maximum Likelihood Constraint Inference for Inverse Reinforcement LearningDexter R. R. Scobee, S. Shankar Sastry. [doi]
• LambdaNet: Probabilistic Type Inference using Graph Neural NetworksJiayi Wei, Maruth Goyal, Greg Durrett, Isil Dillig. [doi]
• Stochastic Weight Averaging in Parallel: Large-Batch Training That Generalizes WellVipul Gupta, Santiago Akle Serrano, Dennis DeCoste. [doi]
• Energy-based models for atomic-resolution protein conformationsYilun Du, Joshua Meier, Jerry Ma, Rob Fergus, Alexander Rives. [doi]
• The Local Elasticity of Neural NetworksHangfeng He, Weijie J. Su. [doi]
• Stable Rank Normalization for Improved Generalization in Neural Networks and GANsAmartya Sanyal, Philip H. S. Torr, Puneet K. Dokania. [doi]
• A Signal Propagation Perspective for Pruning Neural Networks at InitializationNamhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, Philip H. S. Torr. [doi]
• Certified Defenses for Adversarial PatchesPing-Yeh Chiang, Renkun Ni, Ahmed Abdelkader, Chen Zhu, Christoph Studer, Tom Goldstein. [doi]
• Finite Depth and Width Corrections to the Neural Tangent KernelBoris Hanin, Mihai Nica. [doi]
• Sign Bits Are All You Need for Black-Box AttacksAbdullah Al-Dujaili, Una-May O'Reilly. [doi]
• Neural Module Networks for Reasoning over TextNitish Gupta, Kevin Lin, Dan Roth, Sameer Singh 0001, Matt Gardner 0001. [doi]
• Variational Template Machine for Data-to-Text GenerationRong Ye, Wenxian Shi, Hao Zhou 0012, Zhongyu Wei, Lei Li 0018. [doi]
• Contrastive Representation DistillationYonglong Tian, Dilip Krishnan, Phillip Isola. [doi]
• ProxSGD: Training Structured Neural Networks under Regularization and ConstraintsYang Yang 0033, Yaxiong Yuan, Avraam Chatzimichailidis, Ruud J. G. van Sloun, Lei Lei 0001, Symeon Chatzinotas. [doi]
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationYixiao Ge, Dapeng Chen, Hongsheng Li. [doi]
• Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase Lipton. [doi]
• Gradient $\ell_1$ Regularization for Quantization RobustnessMilad Alizadeh, Arash Behboodi, Mart van Baalen, Christos Louizos, Tijmen Blankevoort, Max Welling. [doi]
• Exploring Model-based Planning with Policy NetworksTingwu Wang, Jimmy Ba. [doi]
• Implementation Matters in Deep RL: A Case Study on PPO and TRPOLogan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry. [doi]
• Jacobian Adversarially Regularized Networks for RobustnessAlvin Chan, Yi Tay, Yew-Soon Ong, Jie Fu. [doi]
• Emergent Tool Use From Multi-Agent AutocurriculaBowen Baker, Ingmar Kanitscheider, Todor Markov, Yi Wu, Glenn Powell, Bob McGrew, Igor Mordatch. [doi]
• RTFM: Generalising to New Environment Dynamics via ReadingVictor Zhong, Tim Rocktäschel, Edward Grefenstette. [doi]
• I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers AdaptivelyHaotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma. [doi]
• Population-Guided Parallel Policy Search for Reinforcement LearningWhiyoung Jung, Giseung Park, Youngchul Sung. [doi]
• Learning Hierarchical Discrete Linguistic Units from Visually-Grounded SpeechDavid Harwath, Wei-Ning Hsu, James R. Glass. [doi]
• NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture SearchXuanyi Dong, Yi Yang 0001. [doi]
• Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical SpaceAkshatKumar Nigam, Pascal Friederich, Mario Krenn, Alán Aspuru-Guzik. [doi]
• Online and stochastic optimization beyond Lipschitz continuity: A Riemannian approachKimon Antonakopoulos, Elena Veronica Belmega, Panayotis Mertikopoulos. [doi]
• A Framework for robustness Certification of Smoothed Classifiers using F-DivergencesKrishnamurthy (Dj) Dvijotham, Jamie Hayes, Borja Balle, Zico Kolter, Chongli Qin, András György, Kai Xiao, Sven Gowal, Pushmeet Kohli. [doi]
• On the Convergence of FedAvg on Non-IID DataXiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, Zhihua Zhang. [doi]
• Enhancing Transformation-Based Defenses Against Adversarial Attacks with a Distribution ClassifierConnie Kou, Hwee Kuan Lee, Ee-Chien Chang, Teck Khim Ng. [doi]
• Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement LearningNoah Y. Siegel, Jost Tobias Springenberg, Felix Berkenkamp, Abbas Abdolmaleki, Michael Neunert, Thomas Lampe, Roland Hafner, Nicolas Heess, Martin A. Riedmiller. [doi]
• Scalable and Order-robust Continual Learning with Additive Parameter DecompositionJaehong Yoon, Saehoon Kim, Eunho Yang, Sung Ju Hwang. [doi]
• Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural NetworksXin-xing, Long Sha, Pengyu Hong, Zuofeng Shang, Jun S. Liu. [doi]
• Towards neural networks that provably know when they don't knowAlexander Meinke, Matthias Hein 0001. [doi]
• Intriguing Properties of Adversarial Training at ScaleCihang Xie, Alan L. Yuille. [doi]
• CATER: A diagnostic dataset for Compositional Actions & TEmporal ReasoningRohit Girdhar, Deva Ramanan. [doi]
• Deep probabilistic subsampling for task-adaptive compressed sensingIris A. M. Huijben, Bastiaan S. Veeling, Ruud J. G. van Sloun. [doi]
• Robustness Verification for TransformersZhouxing Shi, Huan Zhang, Kai-Wei Chang, Minlie Huang, Cho-Jui Hsieh. [doi]
• Universal Approximation with Certified NetworksMaximilian Baader, Matthew Mirman, Martin T. Vechev. [doi]
• Reinforcement Learning with Competitive Ensembles of Information-Constrained PrimitivesAnirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio. [doi]
• Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. Talukdar. [doi]
• Pre-training Tasks for Embedding-based Large-scale RetrievalWei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, Sanjiv Kumar. [doi]
• Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep NetworksAlejandro Molina 0001, Patrick Schramowski, Kristian Kersting. [doi]
• Generative Ratio Matching NetworksAkash Srivastava, Kai Xu, Michael U. Gutmann, Charles A. Sutton. [doi]
• Reanalysis of Variance Reduced Temporal Difference LearningTengyu Xu, Zhe Wang, Yi Zhou, Yingbin Liang. [doi]
• Empirical Bayes Transductive Meta-Learning with Synthetic GradientsShell Xu Hu, Pablo Garcia-Moreno, Yang Xiao, Xi Shen, Guillaume Obozinski, Neil D. Lawrence, Andreas C. Damianou. [doi]
• Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networksTimothy Tadros, Giri P. Krishnan, Ramyaa Ramyaa, Maxim Bazhenov. [doi]
• PAC Confidence Sets for Deep Neural Networks via Calibrated PredictionSangdon Park, Osbert Bastani, Nikolai Matni, Insup Lee. [doi]
• Gradients as Features for Deep Representation LearningFangzhou Mu, Yingyu Liang, Yin Li. [doi]
• Deep Orientation Uncertainty Learning based on a Bingham LossIgor Gilitschenski, Roshni Sahoo, Wilko Schwarting, Alexander Amini, Sertac Karaman, Daniela Rus. [doi]
• From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from SpeechHyeong-Seok Choi, Changdae Park, Kyogu Lee. [doi]
• RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?Anil Kag, Ziming Zhang, Venkatesh Saligrama. [doi]
• Memory-Based Graph NetworksAmir Hosein Khas Ahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris. [doi]
• Model Based Reinforcement Learning for AtariLukasz Kaiser, Mohammad Babaeizadeh, Piotr Milos, Blazej Osinski, Roy H. Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Afroz Mohiuddin, Ryan Sepassi, George Tucker, Henryk Michalewski. [doi]
• Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement LearningAkanksha Atrey, Kaleigh Clary, David D. Jensen. [doi]
• Neural Text Generation With Unlikelihood TrainingSean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, KyungHyun Cho, Jason Weston. [doi]
• Locality and Compositionality in Zero-Shot LearningTristan Sylvain, Linda Petrini, R. Devon Hjelm. [doi]
• Depth-Width Trade-offs for ReLU Networks via Sharkovsky's TheoremVaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang. [doi]
• Continual Learning with Bayesian Neural Networks for Non-Stationary DataRichard Kurle, Botond Cseke, Alexej Klushyn, Patrick van der Smagt, Stephan Günnemann. [doi]
• DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion FramesErik Wijmans, Abhishek Kadian, Ari Morcos, Stefan Lee, Irfan Essa, Devi Parikh, Manolis Savva, Dhruv Batra. [doi]
• Your classifier is secretly an energy based model and you should treat it like oneWill Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi 0002, Kevin Swersky. [doi]
• Duration-of-Stay Storage Assignment under UncertaintyMichael Lingzhi Li, Elliott Wolf, Daniel Wintz. [doi]
• AtomNAS: Fine-Grained End-to-End Neural Architecture SearchJieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin, Linjie Yang, Alan L. Yuille, Jianchao Yang. [doi]
• Iterative energy-based projection on a normal data manifold for anomaly localizationDavid Dehaene, Oriel Frigo, Sébastien Combrexelle, Pierre Eline. [doi]
• Semantically-Guided Representation Learning for Self-Supervised Monocular DepthVitor Guizilini, Rui Hou, Jie Li, Rares Ambrus, Adrien Gaidon. [doi]
• Rethinking the Hyperparameters for Fine-tuningHao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto. [doi]
• A Constructive Prediction of the Generalization Error Across ScalesJonathan S. Rosenfeld, Amir Rosenfeld, Yonatan Belinkov, Nir Shavit. [doi]
• Curvature Graph NetworkZe Ye, Kin Sum Liu, Tengfei Ma, Jie Gao 0001, Chao Chen 0012. [doi]
• B-Spline CNNs on Lie groupsErik J. Bekkers. [doi]
• Efficient Probabilistic Logic Reasoning with Graph Neural NetworksYuyu Zhang, Xinshi Chen, Yuan Yang, Arun Ramamurthy, Bo Li, Yuan Qi, Le Song. [doi]
• On Mutual Information Maximization for Representation LearningMichael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic. [doi]
• Deep Audio Priors Emerge From Harmonic Convolutional NetworksZhoutong Zhang, Yunyun Wang, Chuang Gan, Jiajun Wu 0001, Joshua B. Tenenbaum, Antonio Torralba 0001, William T. Freeman. [doi]
• RNA Secondary Structure Prediction By Learning Unrolled AlgorithmsXinshi Chen, Yu Li 0006, Ramzan Umarov, Xin Gao, Le Song. [doi]
• SNOW: Subscribing to Knowledge via Channel Pooling for Transfer & Lifelong Learning of Convolutional Neural NetworksChungkuk Yoo, Bumsoo Kang, Minsik Cho. [doi]
• Learning deep graph matching with channel-independent embedding and Hungarian attentionTianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li. [doi]
• Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous ControlTsui-Wei Weng, Krishnamurthy (Dj) Dvijotham, Jonathan Uesato, Kai Xiao, Sven Gowal, Robert Stanforth, Pushmeet Kohli. [doi]
• Action Semantics Network: Considering the Effects of Actions in Multiagent SystemsWeixun Wang, Tianpei Yang, Yong Liu, Jianye Hao, Xiaotian Hao, Yujing Hu, Yingfeng Chen, Changjie Fan, Yang Gao. [doi]
• Dynamics-Aware EmbeddingsWilliam Whitney, Rajat Agarwal, KyungHyun Cho, Abhinav Gupta. [doi]
• A Meta-Transfer Objective for Learning to Disentangle Causal MechanismsYoshua Bengio, Tristan Deleu, Nasim Rahaman, Nan Rosemary Ke, Sébastien Lachapelle, Olexa Bilaniuk, Anirudh Goyal, Christopher J. Pal. [doi]
• Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from VideoMiguel Jaques, Michael Burke, Timothy M. Hospedales. [doi]
• Hamiltonian Generative NetworksPeter Toth, Danilo J. Rezende, Andrew Jaegle, Sébastien Racanière, Aleksandar Botev, Irina Higgins. [doi]
• Program Guided AgentShao-Hua Sun, Te-Lin Wu, Joseph J. Lim. [doi]
• Novelty Detection Via BlurringSung-Ik Choi, Sae-Young Chung. [doi]
• Mixout: Effective Regularization to Finetune Large-scale Pretrained Language ModelsCheolhyoung Lee, KyungHyun Cho, Wanmo Kang. [doi]
• A critical analysis of self-supervision, or what we can learn from a single imageYuki Markus Asano, Christian Rupprecht 0001, Andrea Vedaldi. [doi]
• Deep Symbolic Superoptimization Without Human KnowledgeHui Shi, Yang Zhang, Xinyun Chen, Yuandong Tian, Jishen Zhao. [doi]
• ELECTRA: Pre-training Text Encoders as Discriminators Rather Than GeneratorsKevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning. [doi]
• Jelly Bean World: A Testbed for Never-Ending LearningEmmanouil Antonios Platanios, Abulhair Saparov, Tom M. Mitchell. [doi]
• Stochastic AUC Maximization with Deep Neural NetworksMingrui Liu, Zhuoning Yuan, Yiming Ying, Tianbao Yang. [doi]
• GLAD: Learning Sparse Graph RecoveryHarsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinivas Aluru, Han Liu, Le Song. [doi]
• Pure and Spurious Critical Points: a Geometric Study of Linear NetworksMatthew Trager, Kathlén Kohn, Joan Bruna. [doi]
• Harnessing the Power of Infinitely Wide Deep Nets on Small-data TasksSanjeev Arora, Simon S. Du, Zhiyuan Li 0005, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu. [doi]
• Real or Not Real, that is the QuestionYuanbo Xiangli, Yubin Deng, Bo Dai, Chen Change Loy, Dahua Lin. [doi]
• DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence ModelingSachin Mehta, Rik Koncel-Kedziorski, Mohammad Rastegari, Hannaneh Hajishirzi. [doi]
• Reinforced active learning for image segmentationArantxa Casanova, Pedro O. Pinheiro, Negar Rostamzadeh, Christopher J. Pal. [doi]
• Discrepancy Ratio: Evaluating Model Performance When Even Experts Disagree on the TruthIgor Lovchinsky, Alon Daks, Israel Malkin, Pouya Samangouei, Ardavan Saeedi, Yang Liu, Swami Sankaranarayanan, Tomer Gafner, Ben Sternlieb, Patrick Maher, Nathan Silberman. [doi]
• DropEdge: Towards Deep Graph Convolutional Networks on Node ClassificationYu Rong, Wenbing Huang, Tingyang Xu, JunZhou Huang. [doi]
• Automated curriculum generation through setter-solver interactionsSébastien Racanière, Andrew K. Lampinen, Adam Santoro, David P. Reichert, Vlad Firoiu, Timothy P. Lillicrap. [doi]
• Compositional Language Continual LearningYuanpeng Li, Liang Zhao, Kenneth Church, Mohamed Elhoseiny. [doi]
• A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer LearningShahbaz Rezaei, Xin Liu 0002. [doi]
• Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog HistoryYiheng Zhou, Yulia Tsvetkov, Alan W. Black, Zhou Yu. [doi]
• Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural NetworksYu Bai, Jason D. Lee. [doi]
• Generalized Convolutional Forest Networks for Domain Generalization and Visual RecognitionJongbin Ryu, Gitaek Kwon, Ming-Hsuan Yang 0001, Jongwoo Lim. [doi]
• Monotonic Multihead AttentionXutai Ma, Juan Miguel Pino, James Cross, Liezl Puzon, Jiatao Gu. [doi]
• Hypermodels for ExplorationVikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Ian Osband, Zheng Wen, Benjamin Van Roy. [doi]
• Reconstructing continuous distributions of 3D protein structure from cryo-EM imagesEllen D. Zhong, Tristan Bepler, Joseph H. Davis, Bonnie Berger. [doi]
• DiffTaichi: Differentiable Programming for Physical SimulationYuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, Frédo Durand. [doi]
• Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature AttributionNikaash Puri, Sukriti Verma, Piyush Gupta, Dhruv Kayastha, Shripad Deshmukh, Balaji Krishnamurthy, Sameer Singh 0001. [doi]
• Inductive representation learning on temporal graphsDa Xu, Chuanwei Ruan, Evren Körpeoglu, Sushant Kumar, Kannan Achan. [doi]
• GraphSAINT: Graph Sampling Based Inductive Learning MethodHanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, Viktor K. Prasanna. [doi]
• Query-efficient Meta Attack to Deep Neural NetworksJiawei Du, Hu Zhang, Joey Tianyi Zhou, Yi Yang, Jiashi Feng. [doi]
• VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsWeijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai. [doi]
• Latent Normalizing Flows for Many-to-Many Cross-Domain MappingsShweta Mahajan, Iryna Gurevych, Stefan Roth 0001. [doi]
• Discriminative Particle Filter Reinforcement Learning for Complex Partial observationsXiao Ma, Péter Karkus, David Hsu, Wee Sun Lee, Nan Ye. [doi]
• Observational Overfitting in Reinforcement LearningXingyou Song, Yiding Jiang, Stephen Tu, Yilun Du, Behnam Neyshabur. [doi]
• Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDPYuanhao Wang, Kefan Dong, Xiaoyu Chen, Liwei Wang. [doi]
• DBA: Distributed Backdoor Attacks against Federated LearningChulin Xie, Keli Huang, Pin-Yu Chen, Bo Li. [doi]
• Deep neuroethology of a virtual rodentJosh Merel, Diego Aldarondo, Jesse Marshall, Yuval Tassa, Greg Wayne, Bence Olveczky. [doi]
• Training Generative Adversarial Networks from Incomplete Observations using Factorised DiscriminatorsDaniel Stoller, Sebastian Ewert, Simon Dixon. [doi]
• Automatically Discovering and Learning New Visual Categories with Ranking StatisticsKai Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman. [doi]
• Distance-Based Learning from Errors for Confidence CalibrationChen Xing, Sercan Ömer Arik, Zizhao Zhang, Tomas Pfister. [doi]
• The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information BudgetAnirudh Goyal, Yoshua Bengio, Matthew Botvinick, Sergey Levine. [doi]
• FasterSeg: Searching for Faster Real-time Semantic SegmentationWuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang. [doi]
• Estimating counterfactual treatment outcomes over time through adversarially balanced representationsIoana Bica, Ahmed M. Alaa, James Jordon, Mihaela van der Schaar. [doi]
• Distributed Bandit Learning: Near-Optimal Regret with Efficient CommunicationYuanhao Wang, Jiachen Hu, Xiaoyu Chen, Liwei Wang. [doi]
• Sequential Latent Knowledge Selection for Knowledge-Grounded DialogueByeongchang Kim, Jaewoo Ahn, Gunhee Kim. [doi]
• Training Recurrent Neural Networks Online by Learning Explicit State VariablesSomjit Nath, Vincent Liu, Alan Chan, Xin Li, Adam White, Martha White. [doi]
• Disagreement-Regularized Imitation LearningKiante Brantley, Wen Sun, Mikael Henaff. [doi]
• Symplectic Recurrent Neural NetworksZhengdao Chen, Jianyu Zhang, Martín Arjovsky, Léon Bottou. [doi]
• Training binary neural networks with real-to-binary convolutionsBrais Martínez, Jing Yang, Adrian Bulat, Georgios Tzimiropoulos. [doi]
• Extreme Classification via Adversarial Softmax ApproximationRobert Bamler, Stephan Mandt. [doi]
• The intriguing role of module criticality in the generalization of deep networksNiladri S. Chatterji, Behnam Neyshabur, Hanie Sedghi. [doi]
• Dynamic Model Pruning with FeedbackTao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi. [doi]
• Making Sense of Reinforcement Learning and Probabilistic InferenceBrendan O'Donoghue, Ian Osband, Catalin Ionescu. [doi]
• Multi-Agent Interactions Modeling with Correlated PoliciesMinghuan Liu, Ming Zhou, Weinan Zhang 0001, Yuzheng Zhuang, Jun Wang, Wulong Liu, Yong Yu. [doi]
• On the interaction between supervision and self-play in emergent communicationRyan Lowe, Abhinav Gupta 0002, Jakob N. Foerster, Douwe Kiela, Joelle Pineau. [doi]
• Generalization of Two-layer Neural Networks: An Asymptotic ViewpointJimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang. [doi]
• A Generalized Training Approach for Multiagent LearningPaul Muller, Shayegan Omidshafiei, Mark Rowland, Karl Tuyls, Julien Pérolat, Siqi Liu, Daniel Hennes, Luke Marris, Marc Lanctot, Edward Hughes, Zhe Wang, Guy Lever, Nicolas Heess, Thore Graepel, Rémi Munos. [doi]
• FSPool: Learning Set Representations with Featurewise Sort PoolingYan Zhang, Jonathon S. Hare, Adam Prügel-Bennett. [doi]
• BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary ActivationsHyungJun Kim, Kyungsu Kim, Jinseok Kim 0004, Jae-Joon Kim. [doi]
• Effect of Activation Functions on the Training of Overparametrized Neural NetsAbhishek Panigrahi, Abhishek Shetty, Navin Goyal. [doi]
• Abductive Commonsense ReasoningChandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen-tau Yih, Yejin Choi. [doi]
• On Solving Minimax Optimization Locally: A Follow-the-Ridge ApproachYuanhao Wang, Guodong Zhang, Jimmy Ba. [doi]
• Learning Heuristics for Quantified Boolean Formulas through Reinforcement LearningGil Lederman, Markus N. Rabe, Sanjit Seshia, Edward A. Lee. [doi]
• Economy Statistical Recurrent Units For Inferring Nonlinear Granger CausalitySaurabh Khanna, Vincent Y. F. Tan. [doi]
• Graph Neural Networks Exponentially Lose Expressive Power for Node ClassificationKenta Oono, Taiji Suzuki. [doi]
• ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation AnchoringDavid Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel. [doi]
• Learning from Rules Generalizing Labeled ExemplarsAbhijeet Awasthi, Sabyasachi Ghosh, Rasna Goyal, Sunita Sarawagi. [doi]
• A Latent Morphology Model for Open-Vocabulary Neural Machine TranslationDuygu Ataman, Wilker Aziz, Alexandra Birch. [doi]
• Learned Step Size quantizationSteven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, Dharmendra S. Modha. [doi]
• Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D MappingAdam W. Harley, Shrinidhi K. Lakshmikanth, Fangyu Li, Xian Zhou, Hsiao-Yu Fish Tung, Katerina Fragkiadaki. [doi]
• Robust Reinforcement Learning for Continuous Control with Model MisspecificationDaniel J. Mankowitz, Nir Levine, Rae Jeong, Abbas Abdolmaleki, Jost Tobias Springenberg, Yuanyuan Shi, Jackie Kay, Todd Hester, Timothy A. Mann, Martin A. Riedmiller. [doi]
• The Shape of Data: Intrinsic Distance for Data DistributionsAnton Tsitsulin, Marina Munkhoeva, Davide Mottin, Panagiotis Karras, Alexander M. Bronstein, Ivan V. Oseledets, Emmanuel Müller. [doi]
• Sharing Knowledge in Multi-Task Deep Reinforcement LearningCarlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters 0001. [doi]
• A Neural Dirichlet Process Mixture Model for Task-Free Continual LearningSoochan Lee, Junsoo Ha, Dongsu Zhang, Gunhee Kim. [doi]
• Consistency Regularization for Generative Adversarial NetworksHan Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee. [doi]
• Learning To Explore Using Active Neural SLAMDevendra Singh Chaplot, Dhiraj Gandhi, Saurabh Gupta 0001, Abhinav Gupta 0001, Ruslan Salakhutdinov. [doi]
• NAS evaluation is frustratingly hardAntoine Yang, Pedro M. Esperança, Fabio Maria Carlucci. [doi]
• Towards Verified Robustness under Text Deletion InterventionsJohannes Welbl, Po-Sen Huang, Robert Stanforth, Sven Gowal, Krishnamurthy (Dj) Dvijotham, Martin Szummer, Pushmeet Kohli. [doi]
• FSNet: Compression of Deep Convolutional Neural Networks by Filter SummaryYingzhen Yang, Jiahui Yu, Nebojsa Jojic, Jun Huan, Thomas S. Huang. [doi]
• Training individually fair ML models with sensitive subspace robustnessMikhail Yurochkin, Amanda Bower, Yuekai Sun. [doi]
• Towards a Deep Network Architecture for Structured SmoothnessHaroun Habeeb, Oluwasanmi Koyejo. [doi]
• Meta-Learning Deep Energy-Based Memory ModelsSergey Bartunov, Jack W. Rae, Simon Osindero, Timothy P. Lillicrap. [doi]
• Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLPHaonan Yu, Sergey Edunov, Yuandong Tian, Ari S. Morcos. [doi]
• Conditional Learning of Fair RepresentationsHan Zhao 0002, Amanda Coston, Tameem Adel, Geoffrey J. Gordon. [doi]
• On the "steerability" of generative adversarial networksAli Jahanian 0002, Lucy Chai, Phillip Isola. [doi]
• Infinite-horizon Off-Policy Policy Evaluation with Multiple Behavior PoliciesXinyun Chen, Lu Wang, Yizhe Hang, Heng Ge, Hongyuan Zha. [doi]
• Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networksChristopher J. Cueva, Peter Y. Wang, Matthew Chin, Xue-Xin Wei. [doi]
• Deep Learning of Determinantal Point Processes via Proper Spectral Sub-gradientTianshu Yu, Yikang Li, Baoxin Li. [doi]
• Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)Peter Sorrenson, Carsten Rother, Ullrich Köthe. [doi]
• Finding and Visualizing Weaknesses of Deep Reinforcement Learning AgentsChristian Rupprecht 0001, Cyril Ibrahim, Christopher J. Pal. [doi]
• Oblique Decision Trees from Derivatives of ReLU NetworksGuang-He Lee, Tommi S. Jaakkola. [doi]
• Demystifying Inter-Class DisentanglementAviv Gabbay, Yedid Hoshen. [doi]
• Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$Francesco Croce, Matthias Hein 0001. [doi]
• The Curious Case of Neural Text DegenerationAri Holtzman, Jan Buys, Li Du, Maxwell Forbes, Yejin Choi. [doi]
• Differentiable learning of numerical rules in knowledge graphsPo-Wei Wang, Daria Stepanova 0001, Csaba Domokos, J. Zico Kolter. [doi]
• Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural networkTaiji Suzuki, Hiroshi Abe, Tomoaki Nishimura. [doi]
• Drawing Early-Bird Tickets: Toward More Efficient Training of Deep NetworksHaoran You, Chaojian Li, Pengfei Xu 0011, Yonggan Fu, Yue Wang, Xiaohan Chen, Richard G. Baraniuk, Zhangyang Wang, Yingyan Lin. [doi]
• Mixup Inference: Better Exploiting Mixup to Defend Adversarial AttacksTianyu Pang, Kun Xu, Jun Zhu. [doi]
• Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based OptimizationSatrajit Chatterjee. [doi]
• Continual learning with hypernetworksJohannes von Oswald, Christian Henning, João Sacramento, Benjamin F. Grewe. [doi]
• Robust Subspace Recovery Layer for Unsupervised Anomaly DetectionChieh-Hsin Lai, Dongmian Zou, Gilad Lerman. [doi]
• Towards Stabilizing Batch Statistics in Backward Propagation of Batch NormalizationJunjie Yan, Ruosi Wan, Xiangyu Zhang, Wei Zhang 0016, Yichen Wei, Jian Sun 0015. [doi]
• Fast is better than free: Revisiting adversarial trainingEric Wong, Leslie Rice, J. Zico Kolter. [doi]
• Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetsDongxian Wu, Yisen Wang 0001, Shu-Tao Xia, James Bailey 0001, Xingjun Ma. [doi]
• Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural NetworksJoonyoung Yi, Juhyuk Lee, Kwang joon Kim, Sung Ju Hwang, Eunho Yang. [doi]
• Fast Neural Network Adaptation via Parameter Remapping and Architecture SearchJiemin Fang, Yuzhu Sun, Kangjian Peng, Qian Zhang, Yuan Li, Wenyu Liu 0001, Xinggang Wang. [doi]
• Counterfactuals uncover the modular structure of deep generative modelsMichel Besserve, Arash Mehrjou, Rémy Sun, Bernhard Schölkopf. [doi]
• A Learning-based Iterative Method for Solving Vehicle Routing ProblemsHao Lu, Xingwen Zhang, Shuang Yang. [doi]
• Difference-Seeking Generative Adversarial Network-Unseen Sample GenerationYi-Lin Sung, Sung-Hsien Hsieh, Soo-Chang Pei, Chun-Shien Lu. [doi]
• DeepSphere: a graph-based spherical CNNMichaël Defferrard, Martino Milani, Frédérick Gusset, Nathanaël Perraudin. [doi]
• Pay Attention to Features, Transfer Learn Faster CNNsKafeng Wang, Xitong Gao, Yiren Zhao, Xingjian Li 0002, Dejing Dou, Cheng-Zhong Xu 0001. [doi]
• On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex LearningJian Li, Xuanyuan Luo, Mingda Qiao. [doi]
• DeepV2D: Video to Depth with Differentiable Structure from MotionZachary Teed, Jia Deng. [doi]
• Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction DetectionMichael Tsang, Dehua Cheng, Hanpeng Liu, Xue Feng, Eric Zhou, Yan Liu. [doi]
• Neural Outlier Rejection for Self-Supervised Keypoint LearningJiexiong Tang, Hanme Kim, Vitor Guizilini, Sudeep Pillai, Rares Ambrus. [doi]
• Differentiation of Blackbox Combinatorial SolversMarin Vlastelica Pogancic, Anselm Paulus, Vít Musil, Georg Martius, Michal Rolinek. [doi]
• Ae-OT: a New Generative Model based on Extended Semi-discrete Optimal transportDongsheng An, Yang Guo, Na Lei, Zhongxuan Luo, Shing-Tung Yau, Xianfeng Gu. [doi]
• StructPool: Structured Graph Pooling via Conditional Random FieldsHao Yuan, Shuiwang Ji. [doi]
• Frequency-based Search-control in DynaYangchen Pan, Jincheng Mei, Amir Massoud Farahmand. [doi]
• Learning Nearly Decomposable Value Functions Via Communication MinimizationTonghan Wang 0001, Jianhao Wang, Chongyi Zheng, Chongjie Zhang. [doi]
• Sign-OPT: A Query-Efficient Hard-label Adversarial AttackMinhao Cheng, Simranjit Singh, Patrick H. Chen, Pin-Yu Chen, Sijia Liu 0001, Cho-Jui Hsieh. [doi]
• Implementing Inductive bias for different navigation tasks through diverse RNN attrractorsTie Xu, Omri Barak. [doi]
• Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative SamplingYuping Luo, Huazhe Xu, Tengyu Ma. [doi]
• Mogrifier LSTMGábor Melis, Tomás Kociský, Phil Blunsom. [doi]
• SEED RL: Scalable and Efficient Deep-RL with Accelerated Central InferenceLasse Espeholt, Raphaël Marinier, Piotr Stanczyk, Ke Wang, Marcin Michalski. [doi]
• A Closer Look at Deep Policy GradientsAndrew Ilyas, Logan Engstrom, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry. [doi]
• NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture SearchArber Zela, Julien Siems, Frank Hutter. [doi]
• Capsules with Inverted Dot-Product Attention RoutingYao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov. [doi]
• Black-Box Adversarial Attack with Transferable Model-based EmbeddingZhichao Huang, Tong Zhang 0001. [doi]
• AugMix: A Simple Data Processing Method to Improve Robustness and UncertaintyDan Hendrycks, Norman Mu, Ekin Dogus Cubuk, Barret Zoph, Justin Gilmer, Balaji Lakshminarayanan. [doi]
• Making Efficient Use of Demonstrations to Solve Hard Exploration ProblemsÇaglar Gülçehre, Tom Le Paine, Bobak Shahriari, Misha Denil, Matthew D. Hoffman, Hubert Soyer, Richard Tanburn, Steven Kapturowski, Neil C. Rabinowitz, Duncan Williams, Gabriel Barth-Maron, Ziyu Wang 0001, Nando de Freitas, Worlds Team. [doi]
• Self-labelling via simultaneous clustering and representation learningYuki M. Asano, Christian Rupprecht 0001, Andrea Vedaldi. [doi]
• BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, Yoav Artzi. [doi]
• Decoding As Dynamic Programming For Recurrent Autoregressive ModelsNajam Zaidi, Trevor Cohn, Gholamreza Haffari. [doi]
• Learning to Coordinate Manipulation Skills via Skill Behavior DiversificationYoungwoon Lee, Jingyun Yang, Joseph J. Lim. [doi]
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information MaximizationFan-Yun Sun, Jordan Hoffmann, Vikas Verma, Jian Tang 0005. [doi]
• Asymptotics of Wide Networks from Feynman DiagramsEthan Dyer, Guy Gur-Ari. [doi]
• MetaPix: Few-Shot Video RetargetingJessica Lee, Deva Ramanan, Rohit Girdhar. [doi]
• One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum EvaluationShunshi Zhang, Bradly C. Stadie. [doi]
• HiLLoC: lossless image compression with hierarchical latent variable modelsJames Townsend, Thomas Bird, Julius Kunze, David Barber. [doi]
• vq-wav2vec: Self-Supervised Learning of Discrete Speech RepresentationsAlexei Baevski, Steffen Schneider, Michael Auli. [doi]
• CLEVRER: Collision Events for Video Representation and ReasoningKexin Yi, Chuang Gan, Yunzhu Li, Pushmeet Kohli, Jiajun Wu 0001, Antonio Torralba 0001, Joshua B. Tenenbaum. [doi]
• Deep Graph Matching ConsensusMatthias Fey, Jan Eric Lenssen, Christopher Morris 0001, Jonathan Masci, Nils M. Kriege. [doi]
• Data-Independent Neural Pruning via CoresetsBen Mussay, Margarita Osadchy, Vladimir Braverman, Samson Zhou, Dan Feldman. [doi]
• Environmental drivers of systematicity and generalization in a situated agentFelix Hill, Andrew K. Lampinen, Rosalia Schneider, Stephen Clark, Matthew Botvinick, James L. McClelland, Adam Santoro. [doi]
• Sampling-Free Learning of Bayesian Quantized Neural NetworksJiahao Su, Milan Cvitkovic, Furong Huang. [doi]
• Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural NetworksLéopold Cambier, Anahita Bhiwandiwalla, Ting Gong, Oguz H. Elibol, Mehran Nekuii, Hanlin Tang. [doi]
• Weakly Supervised Disentanglement with GuaranteesRui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole. [doi]
• Probability Calibration for Knowledge Graph Embedding ModelsPedro Tabacof, Luca Costabello. [doi]
• Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree SearchAnji Liu, Jianshu Chen, Mingze Yu, Yu Zhai, Xuewen Zhou, Ji Liu. [doi]
• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLAniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals. [doi]
• Federated Adversarial Domain AdaptationXingchao Peng, Zijun Huang, Yizhe Zhu, Kate Saenko. [doi]
• Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring in DataDavid W. Romero, Mark Hoogendoorn. [doi]
• Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph ReasoningXiaoran Xu, Wei Feng, Yunsheng Jiang, Xiaohui Xie, Zhiqing Sun, Zhi-Hong Deng. [doi]
• BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong LearningYeming Wen, Dustin Tran, Jimmy Ba. [doi]
• Functional vs. parametric equivalence of ReLU networksMary Phuong, Christoph H. Lampert. [doi]
• Critical initialisation in continuous approximations of binary neural networksGeorge Stamatescu, Federica Gerace, Carlo Lucibello, Ian G. Fuss, Langford B. White. [doi]
• On Bonus Based Exploration Methods In The Arcade Learning EnvironmentAdrien Ali Taïga, William Fedus, Marlos C. Machado, Aaron C. Courville, Marc G. Bellemare. [doi]
• On the Variance of the Adaptive Learning Rate and BeyondLiyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, Jiawei Han 0001. [doi]
• Maxmin Q-learning: Controlling the Estimation Bias of Q-learningQingfeng Lan, Yangchen Pan, Alona Fyshe, Martha White. [doi]
• Continual Learning with Adaptive Weights (CLAW)Tameem Adel, Han Zhao 0002, Richard E. Turner. [doi]
• Low-dimensional statistical manifold embedding of directed graphsThorben Funke, Tian Guo 0002, Alen Lancic, Nino Antulov-Fantulin. [doi]
• End to End Trainable Active Contours via Differentiable RenderingShir Gur, Tal Shaharabany, Lior Wolf. [doi]
• Encoding word order in complex embeddingsBenyou Wang, Donghao Zhao, Christina Lioma, Qiuchi Li, Peng Zhang, Jakob Grue Simonsen. [doi]
• RaPP: Novelty Detection with Reconstruction along Projection PathwayKi Hyun Kim, Sangwoo Shim, Yongsub Lim, Jongseob Jeon, Jeongwoo Choi, Byungchan Kim, Andre S. Yoon. [doi]
• Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent BackpropagationNitin Rathi, Gopalakrishnan Srinivasan, Priyadarshini Panda, Kaushik Roy 0001. [doi]
• Can gradient clipping mitigate label noise?Aditya Krishna Menon, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar. [doi]
• Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network CompilationByung Hoon Ahn, Prannoy Pilligundla, Amir Yazdanbakhsh, Hadi Esmaeilzadeh. [doi]
• Expected Information Maximization: Using the I-Projection for Mixture Density EstimationPhilipp Becker, Oleg Arenz, Gerhard Neumann. [doi]
• PCMC-Net: Feature-based Pairwise Choice Markov ChainsAlix Lhéritier. [doi]
• Smoothness and Stability in GANsCasey Chu, Kentaro Minami, Kenji Fukumizu. [doi]
• Smooth markets: A basic mechanism for organizing gradient-based learnersDavid Balduzzi, Wojciech M. Czarnecki, Tom Anthony, Ian M. Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel. [doi]
• On the Need for Topology-Aware Generative Models for Manifold-Based DefensesUyeong Jang, Susmit Jha, Somesh Jha. [doi]
• Truth or backpropaganda? An empirical investigation of deep learning theoryMicah Goldblum, Jonas Geiping, Avi Schwarzschild, Michael Moeller, Tom Goldstein. [doi]
• Neural Oblivious Decision Ensembles for Deep Learning on Tabular DataSergei Popov, Stanislav Morozov, Artem Babenko. [doi]
• Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked LayersJunjie Liu, Zhe Xu, Runbin Shi, Ray C. C. Cheung, Hayden Kwok-Hay So. [doi]
• Adjustable Real-time Style TransferMohammad Babaeizadeh, Golnaz Ghiasi. [doi]
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question AnsweringAkari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, Caiming Xiong. [doi]
• Overlearning Reveals Sensitive AttributesCongzheng Song, Vitaly Shmatikov. [doi]
• Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point CloudsLukas Prantl, Nuttapong Chentanez, Stefan Jeschke, Nils Thuerey. [doi]
• Adversarial Policies: Attacking Deep Reinforcement LearningAdam Gleave, Michael Dennis, Cody Wild, Neel Kant, Sergey Levine, Stuart Russell. [doi]
• Learning Compositional Koopman Operators for Model-Based ControlYunzhu Li, Hao He, Jiajun Wu 0001, Dina Katabi, Antonio Torralba 0001. [doi]
• Mutual Information Gradient Estimation for Representation LearningLiangjian Wen, Yiji Zhou, Lirong He, Mingyuan Zhou, Zenglin Xu. [doi]
• Short and Sparse Deconvolution - A Geometric ApproachYenson Lau, Qing Qu, Han-Wen Kuo, Pengcheng Zhou, Yuqian Zhang, John Wright 0001. [doi]
• The Gambler's Problem and BeyondBaoxiang Wang, Shuai Li 0010, Jiajin Li, Siu On Chan. [doi]
• Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial NetsMingrui Liu, Youssef Mroueh, Jerret Ross, Wei Zhang, Xiaodong Cui, Payel Das, Tianbao Yang. [doi]
• Functional Regularisation for Continual Learning with Gaussian ProcessesMichalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh. [doi]
• RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated EnvironmentsRoberta Raileanu, Tim Rocktäschel. [doi]
• Contrastive Learning of Structured World ModelsThomas N. Kipf, Elise van der Pol, Max Welling. [doi]
• Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal GenerationSuraj Nair, Chelsea Finn. [doi]
• Learning the Arrow of Time for Problems in Reinforcement LearningNasim Rahaman, Steffen Wolf, Anirudh Goyal, Roman Remme, Yoshua Bengio. [doi]
• Black-box Off-policy Estimation for Infinite-Horizon Reinforcement LearningAli Mousavi, Lihong Li 0001, Qiang Liu, Denny Zhou. [doi]
• Lazy-CFR: fast and near-optimal regret minimization for extensive games with imperfect informationYichi Zhou, Tongzheng Ren, Jialian Li, Dong Yan, Jun Zhu. [doi]
• Nesterov Accelerated Gradient and Scale Invariance for Adversarial AttacksJiadong Lin, Chuanbiao Song, Kun He 0001, Liwei Wang 0001, John E. Hopcroft. [doi]
• GAT: Generative Adversarial Training for Adversarial Example Detection and Robust ClassificationXuwang Yin, Soheil Kolouri, Gustavo K. Rohde. [doi]
• Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous DrivingYurong You, Yan Wang 0051, Wei-Lun Chao, Divyansh Garg, Geoff Pleiss, Bharath Hariharan, Mark E. Campbell, Kilian Q. Weinberger. [doi]
• Measuring and Improving the Use of Graph Information in Graph Neural NetworksYifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma, Hongzhi Chen, Ming-Chang Yang. [doi]
• Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement LearningQian Long, Zihan Zhou, Abhinav Gupta 0001, Fei Fang, Yi Wu, Xiaolong Wang 0004. [doi]
• Bayesian Meta Sampling for Fast Uncertainty AdaptationZhenyi Wang, Yang Zhao, Ping Yu, Ruiyi Zhang, Changyou Chen. [doi]
• Residual Energy-Based Models for Text GenerationYuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam, Marc'Aurelio Ranzato. [doi]
• Diverse Trajectory Forecasting with Determinantal Point ProcessesYe Yuan 0007, Kris M. Kitani. [doi]
• Masked Based Unsupervised Content TransferRon Mokady, Sagie Benaim, Lior Wolf, Amit Bermano. [doi]
• Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill DiscoveryKristian Hartikainen, Xinyang Geng, Tuomas Haarnoja, Sergey Levine. [doi]
• Learning transport cost from subset correspondenceRuiShan Liu, Akshay Balsubramani, James Zou. [doi]
• Meta Reinforcement Learning with Autonomous Inference of Subtask DependenciesSungryull Sohn, Hyunjae Woo, Jongwook Choi, Honglak Lee. [doi]
• Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O KernelXin Qiu, Elliot Meyerson, Risto Miikkulainen. [doi]
• Learning to Learn by Zeroth-Order OracleYangjun Ruan, Yuanhao Xiong, Sashank J. Reddi, Sanjiv Kumar, Cho-Jui Hsieh. [doi]
• Depth-Adaptive TransformerMaha Elbayad, Jiatao Gu, Edouard Grave, Michael Auli. [doi]
• Transferable Perturbations of Deep Feature DistributionsNathan Inkawhich, Kevin J. Liang, Lawrence Carin, Yiran Chen. [doi]
• Synthesizing Programmatic Policies that Inductively GeneralizeJeevana Priya Inala, Osbert Bastani, Zenna Tavares, Armando Solar-Lezama. [doi]
• Decentralized Deep Learning with Arbitrary Communication CompressionAnastasia Koloskova, Tao Lin, Sebastian U. Stich, Martin Jaggi. [doi]
• Lagrangian Fluid Simulation with Continuous ConvolutionsBenjamin Ummenhofer, Lukas Prantl, Nils Thuerey, Vladlen Koltun. [doi]
• Large Batch Optimization for Deep Learning: Training BERT in 76 minutesYang You, Jing Li, Sashank J. Reddi, Jonathan Hseu, Sanjiv Kumar, Srinadh Bhojanapalli, Xiaodan Song, James Demmel, Kurt Keutzer, Cho-Jui Hsieh. [doi]
• Reformer: The Efficient TransformerNikita Kitaev, Lukasz Kaiser, Anselm Levskaya. [doi]
• Relational State-Space Model for Stochastic Multi-Object SystemsFan Yang, Ling Chen 0001, Fan Zhou, Yusong Gao, Wei Cao. [doi]
• Discovering Motor Programs by Recomposing DemonstrationsTanmay Shankar, Shubham Tulsiani, Lerrel Pinto, Abhinav Gupta 0001. [doi]
• Tensor Decompositions for Temporal Knowledge Base CompletionTimothée Lacroix, Guillaume Obozinski, Nicolas Usunier. [doi]
• Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized SmoothingJinyuan Jia, Xiaoyu Cao, Binghui Wang, Neil Zhenqiang Gong. [doi]
• Model-Augmented Actor-Critic: Backpropagating through PathsIgnasi Clavera, Yao Fu, Pieter Abbeel. [doi]
• Robust anomaly detection and backdoor attack detection via differential privacyMin Du, Ruoxi Jia, Dawn Song. [doi]
• SlowMo: Improving Communication-Efficient Distributed SGD with Slow MomentumJianyu Wang, Vinayak Tantia, Nicolas Ballas, Michael Rabbat. [doi]
• Global Relational Models of Source CodeVincent J. Hellendoorn, Charles Sutton, Rishabh Singh, Petros Maniatis, David Bieber. [doi]
• Information Geometry of Orthogonal Initializations and TrainingPiotr Aleksander Sokól, Il Memming Park. [doi]
• Kernel of CycleGAN as a principal homogeneous spaceNikita Moriakov, Jonas Adler, Jonas Teuwen. [doi]
• Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision ActivationsYichi Zhang, Ritchie Zhao, Weizhe Hua, Nayun Xu, G. Edward Suh, Zhiru Zhang. [doi]
• Never Give Up: Learning Directed Exploration StrategiesAdrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Bilal Piot, Steven Kapturowski, Olivier Tieleman, Martín Arjovsky, Alexander Pritzel, Andrew Bolt, Charles Blundell. [doi]
• Watch, Try, Learn: Meta-Learning from Demonstrations and RewardsAllan Zhou, Eric Jang, Daniel Kappler, Alexander Herzog, Mohi Khansari, Paul Wohlhart, Yunfei Bai, Mrinal Kalakrishnan, Sergey Levine, Chelsea Finn. [doi]
• Multilingual Alignment of Contextual Word RepresentationsSteven Cao, Nikita Kitaev, Dan Klein. [doi]
• Generalization bounds for deep convolutional neural networksPhilip M. Long, Hanie Sedghi. [doi]
• Directional Message Passing for Molecular GraphsJohannes Klicpera, Janek Groß, Stephan Günnemann. [doi]
• Learning to Guide Random SearchOzan Sener, Vladlen Koltun. [doi]
• Editable Neural NetworksAnton Sinitsin, Vsevolod Plokhotnyuk, Dmitriy Pyrkin, Sergei Popov, Artem Babenko. [doi]
• Geom-GCN: Geometric Graph Convolutional NetworksHongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang. [doi]
• Disentangling Factors of Variations Using Few LabelsFrancesco Locatello, Michael Tschannen, Stefan Bauer, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem. [doi]
• Learning Execution through Neural Code fusionZhan Shi, Kevin Swersky, Daniel Tarlow, Parthasarathy Ranganathan, Milad Hashemi. [doi]
• Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout ClassificationBennet Breier, Arno Onken. [doi]
• The Early Phase of Neural Network TrainingJonathan Frankle, David J. Schwab, Ari S. Morcos. [doi]
• Combining Q-Learning and Search with Amortized Value EstimatesJessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Theophane Weber, Lars Buesing, Peter W. Battaglia. [doi]
• Ensemble Distribution DistillationAndrey Malinin, Bruno Mlodozeniec, Mark J. F. Gales. [doi]
• Picking Winning Tickets Before Training by Preserving Gradient FlowChaoqi Wang, Guodong Zhang, Roger B. Grosse. [doi]
• Implicit Bias of Gradient Descent based Adversarial Training on Separable DataYan Li, Ethan X. Fang, Huan Xu, Tuo Zhao. [doi]
• Deep 3D Pan via local adaptive "t-shaped" convolutions with global and local adaptive dilationsJuan Luis Gonzalez Bello, Munchurl Kim. [doi]
• Low-Resource Knowledge-Grounded Dialogue GenerationXueliang Zhao, Wei Wu, Chongyang Tao, Can Xu, Dongyan Zhao 0001, Rui Yan 0001. [doi]
• Scale-Equivariant Steerable NetworksIvan Sosnovik, Michal Szmaja, Arnold W. M. Smeulders. [doi]
• SAdam: A Variant of Adam for Strongly Convex FunctionsGuanghui Wang, Shiyin Lu, Quan Cheng, Weiwei Tu, Lijun Zhang 0005. [doi]