Table of Contents

• Efficient Algorithms for Non-convex Isotonic Regression through Submodular OptimizationFrancis Bach. 1-10 [doi]
• Structure-Aware Convolutional Neural NetworksJianlong Chang, Jie Gu, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, Chunhong Pan. 11-20 [doi]
• Kalman Normalization: Normalizing Internal Representations Across Network LayersGuangrun Wang, Jiefeng Peng, Ping Luo 0002, Xinjiang Wang, Liang Lin. 21-31 [doi]
• HOGWILD!-Gibbs can be PanAccurateConstantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti. 32-41 [doi]
• Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural LanguageSeonghyeon Nam, Yunji Kim, Seon Joo Kim. 42-51 [doi]
• IntroVAE: Introspective Variational Autoencoders for Photographic Image SynthesisHuaibo Huang, Zhihang Li, Ran He, Zhenan Sun, Tieniu Tan. 52-63 [doi]
• Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with \beta-DivergencesJeremias Knoblauch, Jack Jewson, Theodoros Damoulas. 64-75 [doi]
• Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer LearningTyler R. Scott, Karl Ridgeway, Michael C. Mozer. 76-85 [doi]
• Generalized Inverse Optimization through Online LearningChaosheng Dong, Yiran Chen, Bo Zeng. 86-95 [doi]
• An Off-policy Policy Gradient Theorem Using Emphatic WeightingsEhsan Imani, Eric Graves, Martha White. 96-106 [doi]
• Supervised autoencoders: Improving generalization performance with unsupervised regularizersLei Le, Andrew Patterson, Martha White. 107-117 [doi]
• Visual Object Networks: Image Generation with Disentangled 3D RepresentationsJun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu 0001, Antonio Torralba 0001, Josh Tenenbaum, Bill Freeman. 118-129 [doi]
• Understanding Weight Normalized Deep Neural Networks with Rectified Linear UnitsYixi Xu, Xiao Wang. 130-139 [doi]
• Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics ProblemsMrinmaya Sachan, Kumar Avinava Dubey, Tom M. Mitchell, Dan Roth, Eric P. Xing. 140-151 [doi]
• Learning long-range spatial dependencies with horizontal gated recurrent unitsDrew Linsley, Junkyung Kim, Vijay Veerabadran, Charles Windolf, Thomas Serre. 152-164 [doi]
• Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-ResolutionZhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang. 165-175 [doi]
• Fast Similarity Search via Optimal Sparse LiftingWenye Li, Jingwei Mao, Yin Zhang, Shuguang Cui. 176-184 [doi]
• Learning Deep Disentangled Embeddings With the F-Statistic LossKarl Ridgeway, Michael C. Mozer. 185-194 [doi]
• Geometrically Coupled Monte Carlo SamplingMark Rowland, Krzysztof Choromanski, François Chalus, Aldo Pacchiano, Tamás Sarlós, Richard E. Turner, Adrian Weller. 195-205 [doi]
• Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose EstimationSiyuan Huang, Siyuan Qi, Yinxue Xiao, Yixin Zhu, Ying Nian Wu, Song Chun Zhu. 206-217 [doi]
• An Efficient Pruning Algorithm for Robust Isotonic RegressionCong Han Lim. 218-227 [doi]
• PAC-learning in the presence of adversariesDaniel Cullina, Arjun Nitin Bhagoji, Prateek Mittal. 228-239 [doi]
• Sparse DNNs with Improved Adversarial RobustnessYiwen Guo, Chao Zhang, Changshui Zhang, Yurong Chen. 240-249 [doi]
• Snap ML: A Hierarchical Framework for Machine LearningCelestine Dünner, Thomas P. Parnell, Dimitrios Sarigiannis, Nikolas Ioannou, Andreea Anghel, Gummadi Ravi, Madhusudanan Kandasamy, Haralampos Pozidis. 250-260 [doi]
• See and Think: Disentangling Semantic Scene CompletionShice Liu, Yu Hu, Yiming Zeng, Qiankun Tang, Beibei Jin, Yinhe Han, Xiaowei Li. 261-272 [doi]
• Chain of Reasoning for Visual Question AnsweringChenfei Wu, Jinlai Liu, Xiaojie Wang, Xuan Dong. 273-283 [doi]
• Sigsoftmax: Reanalysis of the Softmax BottleneckSekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka, Shuichi Adachi. 284-294 [doi]
• Deep Non-Blind Deconvolution via Generalized Low-Rank ApproximationWenqi Ren, Jiawei Zhang, Lin Ma 0002, Jinshan Pan, Xiaochun Cao, Wangmeng Zuo, Wei Liu, Ming-Hsuan Yang 0001. 295-305 [doi]
• Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMCTolga Birdal, Umut Simsekli, Mustafa Onur Eken, Slobodan Ilic. 306-317 [doi]
• MetaAnchor: Learning to Detect Objects with Customized AnchorsTong Yang, Xiangyu Zhang, Zeming Li, Wenqiang Zhang, Jian Sun. 318-328 [doi]
• Image Inpainting via Generative Multi-column Convolutional Neural NetworksYi Wang, Xin Tao, Xiaojuan Qi, Xiaoyong Shen, Jiaya Jia. 329-338 [doi]
• On Misinformation Containment in Online Social NetworksGuangmo Amo Tong, Ding-Zhu Du, Weili Wu. 339-349 [doi]
• A^2-Nets: Double Attention NetworksYunpeng Chen, Yannis Kalantidis, Jianshu Li, Shuicheng Yan, Jiashi Feng. 350-359 [doi]
• Self-Supervised Generation of Spatial Audio for 360° VideoPedro Morgado, Nuno Vasconcelos, Timothy R. Langlois, Oliver Wang. 360-370 [doi]
• How Many Samples are Needed to Estimate a Convolutional Neural Network?Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan R. Salakhutdinov, Aarti Singh. 371-381 [doi]
• Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically BalancedSimon S. Du, Wei Hu, Jason D. Lee. 382-393 [doi]
• Optimization for Approximate SubmodularityYaron Singer, Avinatan Hassidim. 394-405 [doi]
• (Probably) Concave Graph MatchingHaggai Maron, Yaron Lipman. 406-416 [doi]
• Deep Defense: Training DNNs with Improved Adversarial RobustnessZiang Yan, Yiwen Guo, Changshui Zhang. 417-426 [doi]
• Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart SchemesJunqi Tang, Mohammad Golbabaee, Francis Bach, Mike E. Davies. 427-438 [doi]
• Implicit Reparameterization GradientsMikhail Figurnov, Shakir Mohamed, Andriy Mnih. 439-450 [doi]
• Training DNNs with Hybrid Block Floating PointMario Drumond, Tao Lin, Martin Jaggi, Babak Falsafi. 451-461 [doi]
• A Model for Learned Bloom Filters and Optimizing by SandwichingMichael Mitzenmacher. 462-471 [doi]
• Soft-Gated Warping-GAN for Pose-Guided Person Image SynthesisHaoye Dong, Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, Jian Yin. 472-482 [doi]
• Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from FunctionsMinhyuk Sung, Hao Su, Ronald Yu, Leonidas J. Guibas. 483-493 [doi]
• Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal ModelingYunzhe Tao, Qi Sun, Qiang Du, Wei Liu. 494-504 [doi]
• Are ResNets Provably Better than Linear Predictors?Ohad Shamir. 505-514 [doi]
• Learning to Decompose and Disentangle Representations for Video PredictionJun-Ting Hsieh, Bingbin Liu, De-An Huang, Fei-Fei Li, Juan Carlos Niebles. 515-524 [doi]
• Multi-Task Learning as Multi-Objective OptimizationOzan Sener, Vladlen Koltun. 525-536 [doi]
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree SearchZhuwen Li, Qifeng Chen, Vladlen Koltun. 537-546 [doi]
• Self-Erasing Network for Integral Object AttentionQibin Hou, Peng-Tao Jiang, Yunchao Wei, Ming-Ming Cheng. 547-557 [doi]
• LinkNet: Relational Embedding for Scene GraphSanghyun Woo, Dahun Kim, Donghyeon Cho, In-So Kweon. 558-568 [doi]
• How to Start Training: The Effect of Initialization and ArchitectureBoris Hanin, David Rolnick. 569-579 [doi]
• Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients?Boris Hanin. 580-589 [doi]
• Explanations based on the Missing: Towards Contrastive Explanations with Pertinent NegativesAmit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun Chen Tu, Pai-Shun Ting, Karthikeyan Shanmugam, Payel Das. 590-601 [doi]
• HitNet: Hybrid Ternary Recurrent Neural NetworkPeiqi Wang, Xinfeng Xie, Lei Deng, Guoqi Li, Dongsheng Wang, Yuan Xie. 602-612 [doi]
• A Unified Framework for Extensive-Form Game Abstraction with BoundsChristian Kroer, Tuomas Sandholm. 613-624 [doi]
• Removing the Feature Correlation Effect of Multiplicative NoiseZijun Zhang, Yining Zhang, Zongpeng Li. 625-634 [doi]
• Maximum-Entropy Fine Grained ClassificationAbhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Nikhil Naik. 635-645 [doi]
• On Learning Markov ChainsYi Hao, Alon Orlitsky, Venkatadheeraj Pichapati. 646-655 [doi]
• A Neural Compositional Paradigm for Image CaptioningBo Dai, Sanja Fidler, Dahua Lin. 656-666 [doi]
• Quantifying Learning Guarantees for Convex but Inconsistent SurrogatesKirill Struminsky, Simon Lacoste-Julien, Anton Osokin. 667-675 [doi]
• Dialog-based Interactive Image RetrievalXiaoxiao Guo, Hui Wu, Yu Cheng, Steven Rennie, Gerald Tesauro, Rogério Schmidt Feris. 676-686 [doi]
• SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential EstimatorCong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang. 687-697 [doi]
• Are GANs Created Equal? A Large-Scale StudyMario Lucic, Karol Kurach, Marcin Michalski, Sylvain Gelly, Olivier Bousquet. 698-707 [doi]
• Learning Disentangled Joint Continuous and Discrete RepresentationsEmilien Dupont. 708-718 [doi]
• TADAM: Task dependent adaptive metric for improved few-shot learningBoris N. Oreshkin, Pau Rodríguez López, Alexandre Lacoste. 719-729 [doi]
• Do Less, Get More: Streaming Submodular Maximization with SubsamplingMoran Feldman, Amin Karbasi, Ehsan Kazemi 0001. 730-740 [doi]
• Sparse Covariance Modeling in High Dimensions with Gaussian ProcessesRui Li 0002, Kishan KC, Feng Cui, Justin Domke, Anne R. Haake. 741-750 [doi]
• Deep Neural Nets with Interpolating Function as Output ActivationBao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley Osher. 751-761 [doi]
• FishNet: A Versatile Backbone for Image, Region, and Pixel Level PredictionShuyang Sun, Jiangmiao Pang, Jianping Shi, Shuai Yi, Wanli Ouyang. 762-772 [doi]
• Visual Memory for Robust Path FollowingAshish Kumar, Saurabh Gupta, David F. Fouhey, Sergey Levine, Jitendra Malik. 773-782 [doi]
• KDGAN: Knowledge Distillation with Generative Adversarial NetworksXiaojie Wang, Rui Zhang, Yu Sun 0021, Jianzhong Qi. 783-794 [doi]
• Long short-term memory and Learning-to-learn in networks of spiking neuronsGuillaume Bellec, Darjan Salaj, Anand Subramoney, Robert A. Legenstein, Wolfgang Maass 0001. 795-805 [doi]
• Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNNShupeng Su, Chao Zhang, Kai Han, YongHong Tian. 806-815 [doi]
• Informative Features for Model ComparisonWittawat Jitkrittum, Heishiro Kanagawa, Patsorn Sangkloy, James Hays, Bernhard Schölkopf, Arthur Gretton. 816-827 [doi]
• PointCNN: Convolution On X-Transformed PointsYangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen. 828-838 [doi]
• Connectionist Temporal Classification with Maximum Entropy RegularizationHu Liu, Sheng Jin, Changshui Zhang. 839-849 [doi]
• Large Margin Deep Networks for ClassificationGamaleldin F. Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan, Samy Bengio. 850-860 [doi]
• Generalizing Graph Matching beyond Quadratic Assignment ModelTianshu Yu, Junchi Yan, Yilin Wang, Wei Liu, Baoxin Li. 861-871 [doi]
• Solving Large Sequential Games with the Excessive Gap TechniqueChristian Kroer, Gabriele Farina, Tuomas Sandholm. 872-882 [doi]
• Discrimination-aware Channel Pruning for Deep Neural NetworksZhuangwei Zhuang, Mingkui Tan, Bohan Zhuang, Jing Liu, Yong Guo, Qingyao Wu, JunZhou Huang, Jin-Hui Zhu. 883-894 [doi]
• On the Dimensionality of Word EmbeddingZi Yin, Yuanyuan Shen. 895-906 [doi]
• Reinforced Continual LearningJu Xu, Zhanxing Zhu. 907-916 [doi]
• Uncertainty-Aware Attention for Reliable Interpretation and PredictionJay Heo, Haebeom Lee, Saehoon Kim, Juho Lee, Kwang joon Kim, Eunho Yang, Sung Ju Hwang. 917-926 [doi]
• DropMax: Adaptive Variational SoftmaxHaebeom Lee, Juho Lee, Saehoon Kim, Eunho Yang, Sung Ju Hwang. 927-937 [doi]
• Posterior Concentration for Sparse Deep LearningVeronika Rocková, Nicholas Polson. 938-949 [doi]
• A flexible model for training action localization with varying levels of supervisionGuilhem Chéron, Jean-Baptiste Alayrac, Ivan Laptev, Cordelia Schmid. 950-961 [doi]
• A Deep Bayesian Policy Reuse Approach Against Non-Stationary AgentsYan Zheng, Zhaopeng Meng, Jianye Hao, Zongzhang Zhang, Tianpei Yang, Changjie Fan. 962-972 [doi]
• Empirical Risk Minimization in Non-interactive Local Differential Privacy RevisitedDi Wang 0015, Marco Gaboardi, Jinhui Xu 0001. 973-982 [doi]
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation NetworksHang Gao, Zheng Shou, Alireza Zareian, Hanwang Zhang, Shih-Fu Chang. 983-993 [doi]
• Learning semantic similarity in a continuous spaceMichel Deudon. 994-1005 [doi]
• MetaReg: Towards Domain Generalization using Meta-RegularizationYogesh Balaji, Swami Sankaranarayanan, Rama Chellappa. 1006-1016 [doi]
• Boosted Sparse and Low-Rank Tensor RegressionLifang He 0001, Kun Chen 0002, Wanwan Xu, Jiayu Zhou, Fei Wang. 1017-1026 [doi]
• Domain-Invariant Projection Learning for Zero-Shot RecognitionAn Zhao, Mingyu Ding, Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen. 1027-1038 [doi]
• Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language UnderstandingKexin Yi, Jiajun Wu 0001, Chuang Gan, Antonio Torralba 0001, Pushmeet Kohli, Josh Tenenbaum. 1039-1050 [doi]
• Frequency-Domain Dynamic Pruning for Convolutional Neural NetworksZhenhua Liu, Jizheng Xu, Xiulian Peng, Ruiqin Xiong. 1051-1061 [doi]
• Quadratic Decomposable Submodular Function MinimizationPan Li, Niao He, Olgica Milenkovic. 1062-1072 [doi]
• A Block Coordinate Ascent Algorithm for Mean-Variance OptimizationTengyang Xie, Bo Liu, Yangyang Xu, Mohammad Ghavamzadeh, Yinlam Chow, Daoming Lyu, Daesub Yoon. 1073-1083 [doi]
• \ell_1-regression with Heavy-tailed DistributionsLijun Zhang, Zhi-Hua Zhou. 1084-1094 [doi]
• Neural Nearest Neighbors NetworksTobias Plötz, Stefan Roth 0001. 1095-1106 [doi]
• Efficient nonmyopic batch active searchShali Jiang, Gustavo Malkomes, Matthew Abbott, Benjamin Moseley, Roman Garnett. 1107-1117 [doi]
• A Game-Theoretic Approach to Recommendation Systems with Strategic Content ProvidersOmer Ben-Porat, Moshe Tennenholtz. 1118-1128 [doi]
• Interactive Structure Learning with Structural Query-by-CommitteeChristopher Tosh, Sanjoy Dasgupta. 1129-1139 [doi]
• Global Geometry of Multichannel Sparse Blind Deconvolution on the SphereYanjun Li, Yoram Bresler. 1140-1151 [doi]
• Video-to-Video SynthesisTing-chun Wang, Ming-Yu Liu 0001, Jun-Yan Zhu, Nikolai Yakovenko, Andrew Tao, Jan Kautz, Bryan Catanzaro. 1152-1164 [doi]
• How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGDZeyuan Allen Zhu. 1165-1175 [doi]
• Synthesize Policies for Transfer and Adaptation across Tasks and EnvironmentsHexiang Hu, Liyu Chen, Boqing Gong, Fei Sha. 1176-1185 [doi]
• Adversarial vulnerability for any classifierAlhussein Fawzi, Hamza Fawzi, Omar Fawzi. 1186-1195 [doi]
• Evolution-Guided Policy Gradient in Reinforcement LearningShauharda Khadka, Kagan Tumer. 1196-1208 [doi]
• Toddler-Inspired Visual Object LearningSven Bambach, David J. Crandall, Linda B. Smith, Chen Yu. 1209-1218 [doi]
• Alternating optimization of decision trees, with application to learning sparse oblique treesMiguel Á. Carreira-Perpiñán, Pooya Tavallali. 1219-1229 [doi]
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationYixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, Hongsheng Li. 1230-1241 [doi]
• New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and ConvexityPan Zhou, Xiaotong Yuan, Jiashi Feng. 1242-1251 [doi]
• The Lingering of Gradients: How to Reuse Gradients Over TimeZeyuan Allen Zhu, David Simchi-Levi, Xinshang Wang. 1252-1261 [doi]
• Unsupervised Learning of View-invariant Action RepresentationsJunnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli. 1262-1272 [doi]
• Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision MakingHoda Heidari, Claudio Ferrari, Krishna P. Gummadi, Andreas Krause. 1273-1283 [doi]
• Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural NetworksQilong Wang, Zilin Gao, Jiangtao Xie, Wangmeng Zuo, Peihua Li. 1284-1293 [doi]
• Image-to-image translation for cross-domain disentanglementAbel Gonzalez-Garcia, Joost van de Weijer, Yoshua Bengio. 1294-1305 [doi]
• Gradient Sparsification for Communication-Efficient Distributed OptimizationJianqiao Wangni, Jialei Wang, Ji Liu, Tong Zhang. 1306-1316 [doi]
• Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual DetectionTaylor Mordan, Nicolas Thome, Gilles Henaff, Matthieu Cord. 1317-1329 [doi]
• Adaptive Online Learning in Dynamic EnvironmentsLijun Zhang, Shiyin Lu, Zhi-Hua Zhou. 1330-1340 [doi]
• FRAGE: Frequency-Agnostic Word RepresentationChengYue Gong, Di He, Xu Tan, Tao Qin, Liwei Wang 0001, Tie-Yan Liu. 1341-1352 [doi]
• Generative Neural Machine TranslationHarshil Shah, David Barber. 1353-1362 [doi]
• Found Graph Data and Planted Vertex CoversAustin R. Benson, Jon M. Kleinberg. 1363-1374 [doi]
• Joint Active Feature Acquisition and Classification with Variable-Size Set EncodingHajin Shim, Sung Ju Hwang, Eunho Yang. 1375-1385 [doi]
• Regularization Learning Networks: Deep Learning for Tabular DatasetsIra Shavitt, Eran Segal. 1386-1396 [doi]
• Multitask Boosting for Survival Analysis with Competing RisksAlexis Bellot, Mihaela van der Schaar. 1397-1406 [doi]
• Geometry Based Data GenerationOfir Lindenbaum, Jay S. Stanley III, Guy Wolf, Smita Krishnaswamy. 1407-1418 [doi]
• SLAYER: Spike Layer Error Reassignment in TimeSumit Bam Shrestha, Garrick Orchard. 1419-1428 [doi]
• On Oracle-Efficient PAC RL with Rich ObservationsChristoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford 0001, Robert E. Schapire. 1429-1439 [doi]
• Gradient Descent for Spiking Neural NetworksDongsung Huh, Terrence J. Sejnowski. 1440-1450 [doi]
• Generalizing Tree Probability Estimation via Bayesian NetworksCheng Zhang, Frederick A. Matsen IV. 1451-1460 [doi]
• Where Do You Think You're Going?: Inferring Beliefs about Dynamics from BehaviorSiddharth Reddy, Anca D. Dragan, Sergey Levine. 1461-1472 [doi]
• Designing by Training: Acceleration Neural Network for Fast High-Dimensional ConvolutionLongquan Dai, Liang Tang, Yuan Xie 0006, Jinhui Tang. 1473-1482 [doi]
• Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space LearnersYuxin Chen, Adish Singla, Oisin Mac Aodha, Pietro Perona, Yisong Yue. 1483-1493 [doi]
• A loss framework for calibrated anomaly detection1494-1504 [doi]
• PacGAN: The power of two samples in generative adversarial networksZinan Lin, Ashish Khetan, Giulia C. Fanti, Sewoong Oh. 1505-1514 [doi]
• Variational Memory Encoder-DecoderHung Le, Truyen Tran 0001, Thin Nguyen, Svetha Venkatesh. 1515-1525 [doi]
• Stochastic Composite Mirror Descent: Optimal Bounds with High ProbabilitiesYunwen Lei, Ke Tang. 1526-1536 [doi]
• Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report GenerationYuan Li, Xiaodan Liang, Zhiting Hu, Eric P. Xing. 1537-1547 [doi]
• Overcoming Language Priors in Visual Question Answering with Adversarial RegularizationSainandan Ramakrishnan, Aishwarya Agrawal, Stefan Lee. 1548-1558 [doi]
• Hybrid Knowledge Routed Modules for Large-scale Object DetectionChenhan Jiang, Hang Xu, Xiaodan Liang, Liang Lin. 1559-1570 [doi]
• Bilinear Attention NetworksJin-Hwa Kim, Jaehyun Jun, Byoung-Tak Zhang. 1571-1581 [doi]
• Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential LearningXing Yan, Weizhong Zhang, Lin Ma, Wei Liu, Qi Wu. 1582-1592 [doi]
• Multi-Class Learning: From Theory to AlgorithmJian Li, Yong Liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang. 1593-1602 [doi]
• Multivariate Time Series Imputation with Generative Adversarial NetworksYonghong Luo, Xiangrui Cai, Ying Zhang, Jun Xu, Xiaojie Yuan. 1603-1614 [doi]
• Learning Versatile Filters for Efficient Convolutional Neural NetworksYunhe Wang, Chang Xu, Chunjing Xu, Chao Xu 0006, Dacheng Tao. 1615-1625 [doi]
• Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order OptimizationRobert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich. 1626-1636 [doi]
• DifNet: Semantic Segmentation by Diffusion NetworksPeng Jiang, Fanglin Gu, Yunhai Wang, Changhe Tu, Baoquan Chen. 1637-1646 [doi]
• Conditional Adversarial Domain AdaptationMingsheng Long, Zhangjie Cao, Jianmin Wang 0001, Michael I. Jordan. 1647-1657 [doi]
• Neighbourhood Consensus NetworksIgnacio Rocco, Mircea Cimpoi, Relja Arandjelovic, Akihiko Torii, Tomás Pajdla, Josef Sivic. 1658-1669 [doi]
• Relating Leverage Scores and Density using Regularized Christoffel FunctionsEdouard Pauwels, Francis Bach, Jean-Philippe Vert. 1670-1679 [doi]
• Non-Local Recurrent Network for Image RestorationDing Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, Thomas S. Huang. 1680-1689 [doi]
• Bayesian Semi-supervised Learning with Graph Gaussian ProcessesYin Cheng Ng, Nicolò Colombo, Ricardo Silva. 1690-1701 [doi]
• Foreground Clustering for Joint Segmentation and Localization in Videos and ImagesAbhishek Sharma. 1702-1711 [doi]
• Video Prediction via Selective SamplingJingwei Xu, Bingbing Ni, Xiaokang Yang. 1712-1722 [doi]
• Distilled Wasserstein Learning for Word Embedding and Topic ModelingHongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin. 1723-1732 [doi]
• Learning to Exploit Stability for 3D Scene ParsingYilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, Bill Freeman, Josh Tenenbaum, Jiajun Wu 0001. 1733-1743 [doi]
• Neural Guided Constraint Logic Programming for Program SynthesisLisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William E. Byrd, Matthew Might, Raquel Urtasun, Richard S. Zemel. 1744-1753 [doi]
• Genetic-Gated Networks for Deep Reinforcement LearningSimyung Chang, John Yang, Jaeseok Choi, Nojun Kwak. 1754-1763 [doi]
• Fighting Boredom in Recommender Systems with Linear Reinforcement LearningRomain Warlop, Alessandro Lazaric, Jérémie Mary. 1764-1773 [doi]
• Enhancing the Accuracy and Fairness of Human Decision MakingIsabel Valera, Adish Singla, Manuel Gomez-Rodriguez. 1774-1783 [doi]
• Temporal Regularization for Markov Decision ProcessPierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup. 1784-1794 [doi]
• The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised LearningJesse H. Krijthe, Marco Loog. 1795-1804 [doi]
• Simple random search of static linear policies is competitive for reinforcement learningHoria Mania, Aurelia Guy, Benjamin Recht. 1805-1814 [doi]
• Generating Informative and Diverse Conversational Responses via Adversarial Information MaximizationYizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan, Xiujun Li, Chris Brockett, Bill Dolan. 1815-1825 [doi]
• Entropy and mutual information in models of deep neural networksMarylou Gabrié, Andre Manoel, Clément Luneau, Jean Barbier, Nicolas Macris, Florent Krzakala, Lenka Zdeborová. 1826-1836 [doi]
• Collaborative Learning for Deep Neural NetworksGuocong Song, Wei Chai. 1837-1846 [doi]
• High Dimensional Linear Regression using Lattice Basis ReductionIlias Zadik, David Gamarnik. 1847-1857 [doi]
• Symbolic Graph Reasoning Meets ConvolutionsXiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing. 1858-1868 [doi]
• DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann PriorsArash Vahdat, Evgeny Andriyash, William G. Macready. 1869-1878 [doi]
• Partially-Supervised Image CaptioningPeter Anderson 0001, Stephen Gould, Mark Johnson 0001. 1879-1890 [doi]
• 3D-Aware Scene Manipulation via Inverse GraphicsShunyu Yao, Tzu-Ming Harry Hsu, Jun-Yan Zhu, Jiajun Wu 0001, Antonio Torralba 0001, Bill Freeman, Josh Tenenbaum. 1891-1902 [doi]
• Random Feature Stein DiscrepanciesJonathan H. Huggins, Lester Mackey. 1903-1913 [doi]
• Distributed Stochastic Optimization via Adaptive SGDAshok Cutkosky, Róbert Busa-Fekete. 1914-1923 [doi]
• Precision and Recall for Time SeriesNesime Tatbul, Tae-Jun Lee, Stan Zdonik, Mejbah Alam, Justin Gottschlich. 1924-1934 [doi]
• Deep Attentive Tracking via Reciprocative LearningShi Pu, Yibing Song, Chao Ma 0004, Honggang Zhang, Ming-Hsuan Yang 0001. 1935-1945 [doi]
• Virtual Class Enhanced Discriminative Embedding LearningBinghui Chen, Weihong Deng, Haifeng Shen. 1946-1956 [doi]
• Attention in Convolutional LSTM for Gesture RecognitionLiang Zhang 0010, Guangming Zhu, Lin Mei, Peiyi Shen, Syed Afaq Ali Shah, Mohammed Bennamoun. 1957-1966 [doi]
• Pelee: A Real-Time Object Detection System on Mobile DevicesJun Wang, Tanner A. Bohn, Charles X. Ling. 1967-1976 [doi]
• Universal Growth in Production EconomiesSimina Brânzei, Ruta Mehta, Noam Nisan. 1975 [doi]
• Bayesian Model Selection Approach to Boundary Detection with Non-Local PriorsFei Jiang, Guosheng Yin, Francesca Dominici. 1978-1987 [doi]
• Efficient Stochastic Gradient Hard ThresholdingPan Zhou, Xiaotong Yuan, Jiashi Feng. 1988-1997 [doi]
• SplineNets: Continuous Neural Decision GraphsCem Keskin, Shahram Izadi. 1998-2008 [doi]
• Generalized Zero-Shot Learning with Deep Calibration NetworkShichen Liu, Mingsheng Long, Jianmin Wang 0001, Michael I. Jordan. 2009-2019 [doi]
• Neural Architecture Search with Bayesian Optimisation and Optimal TransportKirthevasan Kandasamy, Willie Neiswanger, Jeff Schneider, Barnabás Póczos, Eric P. Xing. 2020-2029 [doi]
• Embedding Logical Queries on Knowledge GraphsWilliam L. Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, Jure Leskovec. 2030-2041 [doi]
• Learning Optimal Reserve Price against Non-myopic BiddersJinyan Liu, Zhiyi Huang 0002, Xiangning Wang. 2042-2052 [doi]
• Sequential Context Encoding for Duplicate RemovalLu Qi, Shu Liu, Jianping Shi, Jiaya Jia. 2053-2062 [doi]
• Discovery of Latent 3D Keypoints via End-to-end Geometric ReasoningSupasorn Suwajanakorn, Noah Snavely, Jonathan J. Tompson, Mohammad Norouzi 0002. 2063-2074 [doi]
• Nonparametric learning from Bayesian models with randomized objective functionsSimon Lyddon, Stephen Walker, Chris C. Holmes. 2075-2085 [doi]
• SEGA: Variance Reduction via Gradient SketchingFilip Hanzely, Konstantin Mishchenko, Peter Richtárik. 2086-2097 [doi]
• Automatic Program Synthesis of Long Programs with a Learned Garbage CollectorAmit Zohar, Lior Wolf. 2098-2107 [doi]
• One-Shot Unsupervised Cross Domain TranslationSagie Benaim, Lior Wolf. 2108-2118 [doi]
• Regularizing by the Variance of the Activations' Sample-VariancesEtai Littwin, Lior Wolf. 2119-2129 [doi]
• Overlapping Clustering Models, and One (class) SVM to Bind Them AllXueyu Mao 0001, Purnamrita Sarkar, Deepayan Chakrabarti. 2130-2140 [doi]
• Algorithmic Linearly Constrained Gaussian ProcessesMarkus Lange-Hegermann. 2141-2152 [doi]
• DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial LearningRunsheng Yu, Wenyu Liu, Yasen Zhang, Zhi Qu, Deli Zhao, Bo Zhang. 2153-2163 [doi]
• Norm matters: efficient and accurate normalization schemes in deep networksElad Hoffer, Ron Banner, Itay Golan, Daniel Soudry. 2164-2174 [doi]
• Dual Principal Component Pursuit: Improved Analysis and Efficient AlgorithmsZhihui Zhu, Yifan Wang, Daniel P. Robinson, Daniel Q. Naiman, René Vidal, Manolis C. Tsakiris. 2175-2185 [doi]
• MULAN: A Blind and Off-Grid Method for Multichannel Echo RetrievalHelena Peic Tukuljac, Antoine Deleforge, Rémi Gribonval. 2186-2196 [doi]
• Mixture Matrix CompletionDaniel L. Pimentel-Alarcón. 2197-2207 [doi]
• Trajectory Convolution for Action RecognitionYue Zhao, Yuanjun Xiong, Dahua Lin. 2208-2219 [doi]
• The Description Length of Deep Learning modelsLéonard Blier, Yann Ollivier. 2220-2230 [doi]
• A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit ProblemSampath Kannan, Jamie H. Morgenstern, Aaron Roth, Bo Waggoner, Zhiwei Steven Wu. 2231-2241 [doi]
• Revisiting Decomposable Submodular Function Minimization with Incidence RelationsPan Li, Olgica Milenkovic. 2242-2252 [doi]
• A Practical Algorithm for Distributed Clustering and Outlier DetectionJiecao Chen, Erfan Sadeqi Azer, Qin Zhang 0001. 2253-2262 [doi]
• Learning to Reconstruct Shapes from Unseen ClassesXiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Josh Tenenbaum, Bill Freeman, Jiajun Wu 0001. 2263-2274 [doi]
• BourGAN: Generative Networks with Metric EmbeddingsChang Xiao, Peilin Zhong, Changxi Zheng. 2275-2286 [doi]
• Smoothed analysis of the low-rank approach for smooth semidefinite programsThomas Pumir, Samy Jelassi, Nicolas Boumal. 2287-2296 [doi]
• Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement LearningOfir Marom, Benjamin Rosman. 2297-2305 [doi]
• Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolateMikhail Belkin, Daniel J. Hsu, Partha Mitra. 2306-2317 [doi]
• Breaking the Span Assumption Yields Fast Finite-Sum MinimizationRobert Hannah, Yanli Liu, Daniel O'Connor, Wotao Yin. 2318-2327 [doi]
• Structured Local Minima in Sparse Blind DeconvolutionYuqian Zhang, Han-Wen Kuo, John Wright. 2328-2337 [doi]
• GIANT: Globally Improved Approximate Newton Method for Distributed OptimizationShusen Wang, Farbod Roosta-Khorasani, Peng Xu, Michael W. Mahoney. 2338-2348 [doi]
• Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction dataXenia Miscouridou, Francois Caron, Yee Whye Teh. 2349-2358 [doi]
• Non-monotone Submodular Maximization in Exponentially Fewer IterationsEric Balkanski, Adam Breuer, Yaron Singer. 2359-2370 [doi]
• MetaGAN: An Adversarial Approach to Few-Shot LearningRuixiang Zhang, Tong Che, Zoubin Ghahramani, Yoshua Bengio, Yangqiu Song. 2371-2380 [doi]
• Local Differential Privacy for Evolving DataMatthew Joseph, Aaron Roth, Jonathan Ullman, Bo Waggoner. 2381-2390 [doi]
• Gaussian Process Conditional Density EstimationVincent Dutordoir, Hugh Salimbeni, James Hensman, Marc Peter Deisenroth. 2391-2401 [doi]
• Meta-Gradient Reinforcement LearningZhongwen Xu, Hado P. van Hasselt, David Silver. 2402-2413 [doi]
• Modular Networks: Learning to Decompose Neural ComputationLouis Kirsch, Julius Kunze, David Barber. 2414-2423 [doi]
• Learning to Navigate in Cities Without a MapPiotr Mirowski, Matthew Koichi Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, Raia Hadsell. 2424-2435 [doi]
• Query Complexity of Bayesian Private LearningKuang Xu. 2436-2445 [doi]
• A theory on the absence of spurious solutions for nonconvex and nonsmooth optimizationCédric Josz, Yi Ouyang, Richard Y. Zhang, Javad Lavaei, Somayeh Sojoudi. 2446-2454 [doi]
• Recurrent World Models Facilitate Policy EvolutionDavid Ha, Jürgen Schmidhuber. 2455-2467 [doi]
• Ridge Regression and Provable Deterministic Ridge Leverage Score SamplingShannon R. McCurdy. 2468-2477 [doi]
• Wasserstein Variational InferenceLuca Ambrogioni, Umut Güçlü, Yagmur Güçlütürk, Max Hinne, Marcel A. J. van Gerven, Eric Maris. 2478-2487 [doi]
• How Does Batch Normalization Help Optimization?Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, Aleksander Madry. 2488-2498 [doi]
• Verifiable Reinforcement Learning via Policy ExtractionOsbert Bastani, Yewen Pu, Armando Solar-Lezama. 2499-2509 [doi]
• Leveraged volume sampling for linear regressionMichal Derezinski, Manfred K. Warmuth, Daniel J. Hsu. 2510-2519 [doi]
• Model Agnostic Supervised Local ExplanationsGregory Plumb, Denali Molitor, Ameet S. Talwalkar. 2520-2529 [doi]
• A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized CommunicationPeng Jiang, Gagan Agrawal. 2530-2541 [doi]
• Active Learning for Non-Parametric Regression Using Purely Random TreesJack Goetz, Ambuj Tewari, Paul Zimmerman. 2542-2551 [doi]
• Tree-to-tree Neural Networks for Program TranslationXinyun Chen, Chang Liu, Dawn Song. 2552-2562 [doi]
• Batch-Instance Normalization for Adaptively Style-Invariant Neural NetworksHyeonseob Nam, Hyo-Eun Kim. 2563-2572 [doi]
• Structural Causal Bandits: Where to Intervene?Sanghack Lee, Elias Bareinboim. 2573-2583 [doi]
• Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual DialogSang-Woo Lee, Yu-Jung Heo, Byoung-Tak Zhang. 2584-2594 [doi]
• A Unified Feature Disentangler for Multi-Domain Image Translation and ManipulationAlexander H. Liu, Yen-Cheng Liu, Yu-Ying Yeh, Yu-Chiang Frank Wang. 2595-2604 [doi]
• Online Learning with an Unknown Fairness MetricStephen Gillen, Christopher Jung, Michael J. Kearns, Aaron Roth. 2605-2614 [doi]
• Isolating Sources of Disentanglement in Variational AutoencodersTian Qi Chen, Xuechen Li, Roger B. Grosse, David K. Duvenaud. 2615-2625 [doi]
• Contextual bandits with surrogate losses: Margin bounds and efficient algorithmsDylan J. Foster, Akshay Krishnamurthy. 2626-2637 [doi]
• Representation Learning for Treatment Effect Estimation from Observational DataLiuyi Yao, Sheng Li 0001, Yaliang Li, Mengdi Huai, Jing Gao, Aidong Zhang. 2638-2648 [doi]
• Representation Balancing MDPs for Off-policy Policy EvaluationYao Liu, Omer Gottesman, Aniruddh Raghu, Matthieu Komorowski, Aldo A. Faisal, Finale Doshi-Velez, Emma Brunskill. 2649-2658 [doi]
• Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question AnsweringMedhini Narasimhan, Svetlana Lazebnik, Alexander G. Schwing. 2659-2670 [doi]
• Causal Discovery from Discrete Data using Hidden Compact RepresentationRuichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang, Zhifeng Hao. 2671-2679 [doi]
• Natasha 2: Faster Non-Convex Optimization Than SGDZeyuan Allen Zhu. 2680-2691 [doi]
• Minimax Statistical Learning with Wasserstein distancesJaeho Lee, Maxim Raginsky. 2692-2701 [doi]
• Provable Variational Inference for Constrained Log-Submodular ModelsJosip Djolonga, Stefanie Jegelka, Andreas Krause 0001. 2702-2712 [doi]
• Learning Hierarchical Semantic Image Manipulation through Structured RepresentationsSeunghoon Hong, Xinchen Yan, Thomas S. Huang, Honglak Lee. 2713-2723 [doi]
• Processing of missing data by neural networksMarek Smieja, Lukasz Struski, Jacek Tabor, Bartosz Zielinski 0001, Przemyslaw Spurek. 2724-2734 [doi]
• Safe Active Learning for Time-Series Modeling with Gaussian ProcessesChristoph Zimmer, Mona Meister, Duy Nguyen-Tuong. 2735-2744 [doi]
• Optimal Algorithms for Non-Smooth Distributed Optimization in NetworksKevin Scaman, Francis Bach, Sébastien Bubeck, Laurent Massoulié, Yin Tat Lee. 2745-2754 [doi]
• Computing Higher Order Derivatives of Matrix and Tensor ExpressionsSören Laue, Matthias Mitterreiter, Joachim Giesen. 2755-2764 [doi]
• Paraphrasing Complex Network: Network Compression via Factor TransferJangho Kim, Seonguk Park, Nojun Kwak. 2765-2774 [doi]
• Analytic solution and stationary phase approximation for the Bayesian lasso and elastic netTom Michoel. 2775-2785 [doi]
• Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximationChaitanya Ryali, Gautam Reddy, Angela J. Yu. 2786-2795 [doi]
• Empirical Risk Minimization Under Fairness ConstraintsMichele Donini, Luca Oneto, Shai Ben-David, John Shawe-Taylor, Massimiliano Pontil. 2796-2806 [doi]
• Unsupervised Learning of Shape and Pose with Differentiable Point CloudsEldar Insafutdinov, Alexey Dosovitskiy. 2807-2817 [doi]
• Continuous-time Value Function Approximation in Reproducing Kernel Hilbert SpacesMotoya Ohnishi, Masahiro Yukawa, Mikael Johansson, Masashi Sugiyama. 2818-2829 [doi]
• Gradient Descent Meets Shift-and-Invert Preconditioning for Eigenvector ComputationZhiqiang Xu. 2830-2839 [doi]
• Factored BanditsJulian Zimmert, Yevgeny Seldin. 2840-2849 [doi]
• Delta-encoder: an effective sample synthesis method for few-shot object recognitionEli Schwartz, Leonid Karlinsky, Joseph Shtok, Sivan Harary, Mattias Marder, Abhishek Kumar, Rogério Schmidt Feris, Raja Giryes, Alexander M. Bronstein. 2850-2860 [doi]
• Metric on Nonlinear Dynamical Systems with Perron-Frobenius OperatorsIsao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, Yoshinobu Kawahara. 2861-2871 [doi]
• Learning a High Fidelity Pose Invariant Model for High-resolution Face FrontalizationJie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun. 2872-2882 [doi]
• Mirrored Langevin DynamicsYa-Ping Hsieh, Ali Kavis, Paul Rolland, Volkan Cevher. 2883-2892 [doi]
• Moonshine: Distilling with Cheap ConvolutionsElliot J. Crowley, Gavin Gray, Amos J. Storkey. 2893-2903 [doi]
• Stochastic Cubic Regularization for Fast Nonconvex OptimizationNilesh Tripuraneni, Mitchell Stern, Chi Jin, Jeffrey Regier, Michael I. Jordan. 2904-2913 [doi]
• Adaptation to Easy Data in Prediction with Limited AdviceTobias Sommer Thune, Yevgeny Seldin. 2914-2923 [doi]
• Differentially Private Bayesian Inference for Exponential FamiliesGarrett Bernstein, Daniel R. Sheldon. 2924-2934 [doi]
• Playing hard exploration games by watching YouTubeYusuf Aytar, Tobias Pfaff, David Budden, Thomas Paine, Ziyu Wang 0001, Nando de Freitas. 2935-2945 [doi]
• Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge BaseDaya Guo, Duyu Tang, Nan Duan, Ming Zhou, Jian Yin. 2946-2955 [doi]
• Norm-Ranging LSH for Maximum Inner Product SearchXiao Yan, Jinfeng Li, Xinyan Dai, Hongzhi Chen, James Cheng. 2956-2965 [doi]
• Optimization over Continuous and Multi-dimensional Decisions with Observational DataDimitris Bertsimas, Christopher McCord. 2966-2974 [doi]
• Fast Estimation of Causal Interactions using Wold ProcessesFlavio Figueiredo, Guilherme Resende Borges, Pedro O. S. Vaz de Melo, Renato Assunção. 2975-2986 [doi]
• When do random forests fail?Cheng Tang, Damien Garreau, Ulrike von Luxburg. 2987-2997 [doi]
• Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision ProcessesRonan Fruit, Matteo Pirotta, Alessandro Lazaric. 2998-3008 [doi]
• Optimistic optimization of a BrownianJean-Bastien grill, Michal Valko, Rémi Munos. 3009-3018 [doi]
• Practical Methods for Graph Two-Sample TestingDebarghya Ghoshdastidar, Ulrike von Luxburg. 3019-3028 [doi]
• NAIS-Net: Stable Deep Networks from Non-Autonomous Differential EquationsMarco Ciccone, Marco Gallieri, Jonathan Masci, Christian Osendorfer, Faustino J. Gomez. 3029-3039 [doi]
• On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal TransportLénaïc Chizat, Francis Bach. 3040-3050 [doi]
• Constructing Deep Neural Networks by Bayesian Network Structure LearningRaanan Y. Yehezkel Rohekar, Shami Nisimov, Yaniv Gurwicz, Guy Koren, Gal Novik. 3051-3062 [doi]
• Weakly Supervised Dense Event Captioning in VideosXuguang Duan, Wen-bing Huang, Chuang Gan, Jingdong Wang, Wenwu Zhu 0001, JunZhou Huang. 3063-3073 [doi]
• Faithful Inversion of Generative Models for Effective Amortized InferenceStefan Webb, Adam Golinski, Robert Zinkov, Siddharth Narayanaswamy, Tom Rainforth, Yee Whye Teh, Frank Wood. 3074-3084 [doi]
• From Stochastic Planning to Marginal MAPHao Cui, Radu Marinescu, Roni Khardon. 3085-3095 [doi]
• On Binary Classification in Extreme RegionsHamid Jalalzai, Stéphan Clémençon, Anne Sabourin. 3096-3104 [doi]
• Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection ModelsYining Wang, Xi Chen, Yuan Zhou. 3105-3114 [doi]
• Q-learning with Nearest NeighborsDevavrat Shah, Qiaomin Xie. 3115-3125 [doi]
• Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex OptimizationPan Xu, Jinghui Chen, Difan Zou, Quanquan Gu. 3126-3137 [doi]
• Asymptotic optimality of adaptive importance samplingFrançois Portier, Bernard Delyon. 3138-3148 [doi]
• Learning latent variable structured prediction models with Gaussian perturbationsKevin Bello, Jean Honorio. 3149-3159 [doi]
• The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-OptimalJiantao Jiao, Weihao Gao, Yanjun Han. 3160-3171 [doi]
• Deep Reinforcement Learning of Marked Temporal Point ProcessesUtkarsh Upadhyay, Abir De, Manuel Gomez-Rodriguez. 3172-3182 [doi]
• Evidential Deep Learning to Quantify Classification UncertaintyMurat Sensoy, Lance M. Kaplan, Melih Kandemir. 3183-3193 [doi]
• Parsimonious Bayesian deep networksMingyuan Zhou. 3194-3204 [doi]
• Single-Agent Policy Tree Search With GuaranteesLaurent Orseau, Levi Lelis, Tor Lattimore, Theophane Weber. 3205-3215 [doi]
• Semi-crowdsourced Clustering with Deep Generative ModelsYucen Luo, Tian Tian 0001, Jiaxin Shi, Jun Zhu 0001, Bo Zhang. 3216-3226 [doi]
• The committee machine: Computational to statistical gaps in learning a two-layers neural networkBenjamin Aubin, Antoine Maillard, Jean Barbier, Florent Krzakala, Nicolas Macris, Lenka Zdeborová. 3227-3238 [doi]
• Realistic Evaluation of Deep Semi-Supervised Learning AlgorithmsAvital Oliver, Augustus Odena, Colin A. Raffel, Ekin Dogus Cubuk, Ian J. Goodfellow. 3239-3250 [doi]
• Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular RewardLixing Chen, Jie Xu, Zhuo Lu. 3251-3260 [doi]
• Training deep learning based denoisers without ground truth dataShakarim Soltanayev, Se Young Chun. 3261-3271 [doi]
• Re-evaluating evaluationDavid Balduzzi, Karl Tuyls, Julien Pérolat, Thore Graepel. 3272-3283 [doi]
• Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibresOisín Moran, Piergiorgio Caramazza, Daniele Faccio, Roderick Murray-Smith. 3284-3295 [doi]
• Multivariate Convolutional Sparse Coding for Electromagnetic Brain SignalsTom Dupré la Tour, Thomas Moreau, Mainak Jas, Alexandre Gramfort. 3296-3306 [doi]
• Data-Efficient Hierarchical Reinforcement LearningOfir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine. 3307-3317 [doi]
• Speaker-Follower Models for Vision-and-Language NavigationDaniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein, Trevor Darrell. 3318-3329 [doi]
• Inequity aversion improves cooperation in intertemporal social dilemmasEdward Hughes, Joel Z. Leibo, Matthew Phillips, Karl Tuyls, Edgar A. Duéñez-Guzmán, Antonio García Castañeda, Iain Dunning, Tina Zhu, Kevin R. McKee, Raphael Koster, Heather Roff, Thore Graepel. 3330-3340 [doi]
• Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization BoundsDavid Reeb, Andreas Doerr, Sebastian Gerwinn, Barbara Rakitsch. 3341-3351 [doi]
• Probabilistic Matrix Factorization for Automated Machine LearningNicoló Fusi, Rishit Sheth, Melih Elibol. 3352-3361 [doi]
• Stochastic Spectral and Conjugate Descent MethodsDmitry Kovalev, Peter Richtárik, Eduard Gorbunov, Elnur Gasanov. 3362-3371 [doi]
• Recurrent Relational NetworksRasmus Berg Palm, Ulrich Paquet, Ole Winther. 3372-3382 [doi]
• But How Does It Work in Theory? Linear SVM with Random FeaturesYitong Sun, Anna C. Gilbert, Ambuj Tewari. 3383-3392 [doi]
• Learning to Optimize Tensor ProgramsTianQi Chen, Lianmin Zheng, Eddie Q. Yan, Ziheng Jiang, Thierry Moreau, Luis Ceze, Carlos Guestrin, Arvind Krishnamurthy. 3393-3404 [doi]
• Boosting Black Box Variational InferenceFrancesco Locatello, Gideon Dresdner, Rajiv Khanna, Isabel Valera, Gunnar Rätsch. 3405-3415 [doi]
• Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemesHassan Ashtiani, Shai Ben-David, Nicholas J. A. Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan. 3416-3425 [doi]
• Actor-Critic Policy Optimization in Partially Observable Multiagent EnvironmentsSriram Srinivasan, Marc Lanctot, Vinícius Flores Zambaldi, Julien Pérolat, Karl Tuyls, Rémi Munos, Michael Bowling. 3426-3439 [doi]
• Step Size Matters in Deep LearningKamil Nar, Shankar Sastry. 3440-3448 [doi]
• Derivative Estimation in Random DesignYu Liu, Kris De Brabanter. 3449-3458 [doi]
• Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient UpdatesKrishnakumar Balasubramanian, Saeed Ghadimi. 3459-3468 [doi]
• Latent Gaussian Activity Propagation: Using Smoothness and Structure to Separate and Localize Sounds in Large Noisy EnvironmentsDaniel Johnson, Daniel Gorelik, Ross E. Mawhorter, Kyle Suver, Weiqing Gu, Steven Xing, Cody Gabriel, Peter Sankhagowit. 3469-3478 [doi]
• Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference AggregationJing Li 0026, Rafal Mantiuk, Junle Wang, Suiyi Ling, Patrick Le Callet. 3479-3489 [doi]
• Infinite-Horizon Gaussian ProcessesArno Solin, James Hensman, Richard E. Turner. 3490-3499 [doi]
• Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex OptimizationMinshuo Chen, Lin Yang, Mengdi Wang, Tuo Zhao. 3500-3510 [doi]
• Sequence-to-Segment Networks for Segment DetectionZijun Wei, Boyu Wang, Minh Hoai Nguyen, Jianming Zhang, Zhe L. Lin, Xiaohui Shen, Radomír Mech, Dimitris Samaras. 3511-3520 [doi]
• Scaling the Poisson GLM to massive neural datasets through polynomial approximationsDavid M. Zoltowski, Jonathan W. Pillow. 3521-3531 [doi]
• Multiplicative Weights Updates with Constant Step-Size in Graphical Constant-Sum GamesYun Kuen Cheung. 3532-3542 [doi]
• Why Is My Classifier Discriminatory?Irene Chen, Fredrik D. Johansson, David Sontag. 3543-3554 [doi]
• Multi-Layered Gradient Boosting Decision TreesJi Feng, Yang Yu 0001, Zhi-Hua Zhou. 3555-3565 [doi]
• Learn What Not to Learn: Action Elimination with Deep Reinforcement LearningTom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor. 3566-3577 [doi]
• Communication Efficient Parallel Algorithms for Optimization on ManifoldsBayan Saparbayeva, Michael Minyi Zhang, Lizhen Lin. 3578-3588 [doi]
• Neural Code Comprehension: A Learnable Representation of Code SemanticsTal Ben-Nun, Alice Shoshana Jakobovits, Torsten Hoefler. 3589-3601 [doi]
• Tight Bounds for Collaborative PAC Learning via Multiplicative WeightsJiecao Chen, Qin Zhang 0001, Yuan Zhou. 3602-3611 [doi]
• BinGAN: Learning Compact Binary Descriptors with a Regularized GANMaciej Zieba, Piotr Semberecki, Tarek El-Gaaly, Tomasz Trzcinski. 3612-3622 [doi]
• Modern Neural Networks Generalize on Small Data SetsMatthew Olson, Abraham J. Wyner, Richard Berk. 3623-3632 [doi]
• Escaping Saddle Points in Constrained OptimizationAryan Mokhtari, Asuman E. Ozdaglar, Ali Jadbabaie. 3633-3643 [doi]
• Adversarial Attacks on Stochastic BanditsKwang-Sung Jun, Lihong Li 0001, Yuzhe Ma, Xiaojin (Jerry) Zhu. 3644-3653 [doi]
• Optimal Subsampling with Influence FunctionsDaniel Ting, Eric Brochu. 3654-3663 [doi]
• A Bandit Approach to Sequential Experimental Design with False Discovery ControlKevin G. Jamieson, Lalit Jain. 3664-3674 [doi]
• Equality of Opportunity in Classification: A Causal ApproachJunzhe Zhang, Elias Bareinboim. 3675-3685 [doi]
• Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic OptimizationTianyi Liu, Shiyang Li, Jianping Shi, Enlu Zhou, Tuo Zhao. 3686-3696 [doi]
• Unsupervised Attention-guided Image-to-Image TranslationYoussef Alami Mejjati, Christian Richardt, James Tompkin, Darren Cosker, Kwang In Kim. 3697-3707 [doi]
• Inferring Networks From Random Walk-Based Node SimilaritiesJeremy G. Hoskins, Cameron Musco, Christopher Musco, Babis Tsourakakis. 3708-3719 [doi]
• NEON2: Finding Local Minima via First-Order OraclesZeyuan Allen Zhu, Yuanzhi Li. 3720-3730 [doi]
• Zeroth-Order Stochastic Variance Reduction for Nonconvex OptimizationSijia Liu 0001, Bhavya Kailkhura, Pin-Yu Chen, Pai-Shun Ting, Shiyu Chang, Lisa Amini. 3731-3741 [doi]
• Online Structured Laplace Approximations for Overcoming Catastrophic ForgettingHippolyt Ritter, Aleksandar Botev, David Barber. 3742-3752 [doi]
• DeepProbLog: Neural Probabilistic Logic ProgrammingRobin Manhaeve, Sebastijan Dumancic, Angelika Kimmig, Thomas Demeester, Luc De Raedt. 3753-3763 [doi]
• Convergence of Cubic Regularization for Nonconvex Optimization under KL PropertyYi Zhou, Zhe Wang, Yingbin Liang. 3764-3773 [doi]
• Direct Estimation of Differences in Causal GraphsYuhao Wang, Chandler Squires, Anastasiya Belyaeva, Caroline Uhler. 3774-3785 [doi]
• Sublinear Time Low-Rank Approximation of Distance MatricesAinesh Bakshi, David P. Woodruff. 3786-3796 [doi]
• Variational PDEs for Acceleration on Manifolds and Application to DiffeomorphismsGanesh Sundaramoorthi, Anthony J. Yezzi. 3797-3807 [doi]
• Bayesian Inference of Temporal Task Specifications from DemonstrationsAnkit Shah, Pritish Kamath, Julie A. Shah, Shen Li. 3808-3817 [doi]
• Data center cooling using model-predictive controlNevena Lazic, Craig Boutilier, Tyler Lu, Eehern Wong, Binz Roy, M. K. Ryu, Greg Imwalle. 3818-3827 [doi]
• Acceleration through Optimistic No-Regret DynamicsJun-Kun Wang, Jacob D. Abernethy. 3828-3838 [doi]
• Lipschitz regularity of deep neural networks: analysis and efficient estimationAladin Virmaux, Kevin Scaman. 3839-3848 [doi]
• Minimax Estimation of Neural Net DistanceKaiyi Ji, Yingbin Liang. 3849-3858 [doi]
• Leveraging the Exact Likelihood of Deep Latent Variable ModelsPierre-Alexandre Mattei, Jes Frellsen. 3859-3870 [doi]
• Bipartite Stochastic Block Models with Tiny ClustersStefan Neumann 0003. 3871-3881 [doi]
• Learning sparse neural networks via sensitivity-driven regularizationEnzo Tartaglione, Skjalg Lepsøy, Attilio Fiandrotti, Gianluca Francini. 3882-3892 [doi]
• Faster Online Learning of Optimal Threshold for Consistent F-measure OptimizationXiaoxuan Zhang, Mingrui Liu, Xun Zhou, Tianbao Yang. 3893-3903 [doi]
• Direct Runge-Kutta Discretization Achieves AccelerationJingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie. 3904-3913 [doi]
• Adversarial Examples that Fool both Computer Vision and Time-Limited HumansGamaleldin F. Elsayed, Shreya Shankar, Brian Cheung, Nicolas Papernot, Alexey Kurakin, Ian J. Goodfellow, Jascha Sohl-Dickstein. 3914-3924 [doi]
• Stochastic Nested Variance Reduced Gradient Descent for Nonconvex OptimizationDongruo Zhou, Pan Xu, Quanquan Gu. 3925-3936 [doi]
• Faster Neural Networks Straight from JPEGLionel Gueguen, Alex Sergeev, Ben Kadlec, Rosanne Liu, Jason Yosinski. 3937-3948 [doi]
• TopRank: A practical algorithm for online stochastic rankingTor Lattimore, Branislav Kveton, Shuai Li, Csaba Szepesvári. 3949-3958 [doi]
• Learning from discriminative feature feedbackSanjoy Dasgupta, Akansha Dey, Nicholas Roberts, Sivan Sabato. 3959-3967 [doi]
• RetGK: Graph Kernels based on Return Probabilities of Random WalksZhen Zhang 0007, Mianzhi Wang, Yijian Xiang, Yan Huang 0018, Arye Nehorai. 3968-3978 [doi]
• Deep Generative Markov State ModelsHao Wu, Andreas Mardt, Luca Pasquali, Frank Noé. 3979-3988 [doi]
• Early Stopping for Nonparametric TestingMeimei Liu, Guang Cheng. 3989-3998 [doi]
• Solving Non-smooth Constrained Programs with Lower Complexity than \mathcal{O}(1/\varepsilon): A Primal-Dual Homotopy Smoothing ApproachXiaohan Wei, Hao Yu 0002, Qing Ling, Michael J. Neely. 3999-4009 [doi]
• Heterogeneous Bitwidth Binarization in Convolutional Neural NetworksJoshua Fromm, Shwetak Patel, Matthai Philipose. 4010-4019 [doi]
• Unsupervised Learning of Object Landmarks through Conditional Image GenerationTomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi. 4020-4031 [doi]
• Probabilistic Neural Programmed Networks for Scene GenerationZhiwei Deng, Jiacheng Chen, Yifang Fu, Greg Mori. 4032-4042 [doi]
• The streaming rollout of deep networks - towards fully model-parallel executionVolker Fischer, Jan Köhler, Thomas Pfeil. 4043-4054 [doi]
• KONG: Kernels for ordered-neighborhood graphsMoez Draief, Konstantin Kutzkov, Kevin Scaman, Milan Vojnovic. 4055-4064 [doi]
• GumBolt: Extending Gumbel trick to Boltzmann priorsAmir H. Khoshaman, Mohammad H. Amin. 4065-4074 [doi]
• Neural Networks Trained to Solve Differential Equations Learn General RepresentationsMartin Magill, Faisal Qureshi, Hendrick W. de Haan. 4075-4085 [doi]
• Beauty-in-averageness and its contextual modulations: A Bayesian statistical accountChaitanya Ryali, Angela J. Yu. 4086-4096 [doi]
• Distributed Weight Consolidation: A Brain Segmentation Case StudyPatrick McClure, Charles Y. Zheng, Jakub Kaczmarzyk, John Rogers-Lee, Satra Ghosh, Dylan Nielson, Peter A. Bandettini, Francisco Pereira. 4097-4107 [doi]
• Efficient Projection onto the Perfect Phylogeny ModelBei Jia, Surjyendu Ray, Sam Safavi, José Bento. 4108-4118 [doi]
• TETRIS: TilE-matching the TRemendous Irregular SparsityYu Ji, Ling Liang, Lei Deng, Youyang Zhang, Youhui Zhang, Yuan Xie. 4119-4129 [doi]
• Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classificationHarsh Shrivastava, Eugene Bart, Bob Price, Hanjun Dai, Bo Dai, Srinivas Aluru. 4130-4140 [doi]
• Differentially Private Robust Low-Rank ApproximationRaman Arora, Vladimir Braverman, Jalaj Upadhyay. 4141-4149 [doi]
• Meta-Learning MCMC ProposalsTongzhou Wang, Yi Wu, Dave Moore, Stuart J. Russell. 4150-4160 [doi]
• An Information-Theoretic Analysis for Thompson Sampling with Many ActionsShi Dong, Benjamin Van Roy. 4161-4169 [doi]
• Flexible and accurate inference and learning for deep generative modelsEszter Vértes, Maneesh Sahani. 4170-4179 [doi]
• The Price of Privacy for Low-rank FactorizationJalaj Upadhyay. 4180-4191 [doi]
• Regret Bounds for Robust Adaptive Control of the Linear Quadratic RegulatorSarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu. 4192-4201 [doi]
• Bilevel Distance Metric Learning for Robust Image RecognitionJie Xu, Lei Luo, Cheng Deng, Heng Huang. 4202-4211 [doi]
• Differentially Private Uniformly Most Powerful Tests for Binomial DataJordan Awan, Aleksandra Slavkovic. 4212-4222 [doi]
• Scalable Coordinated Exploration in Concurrent Reinforcement LearningMaria Dimakopoulou, Ian Osband, Benjamin Van Roy. 4223-4232 [doi]
• Integrated accounts of behavioral and neuroimaging data using flexible recurrent neural network modelsAmir Dezfouli, Richard W. Morris, Fabio T. Ramos, Peter Dayan, Bernard W. Balleine. 4233-4242 [doi]
• BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML TrainingSongtao Wang, Dan Li, Yang Cheng, Jinkun Geng, Yanshu Wang, Shuai Wang, Shu-Tao Xia, Jianping Wu. 4243-4253 [doi]
• Inexact trust-region algorithms on Riemannian manifoldsHiroyuki Kasai, Bamdev Mishra. 4254-4265 [doi]
• Can We Gain More from Orthogonality Regularizations in Training Deep Networks?Nitin Bansal, Xiaohan Chen, Zhangyang Wang. 4266-4276 [doi]
• Binary Rating Estimation with Graph Side InformationKwangjun Ahn, Kangwook Lee, Hyunseung Cha, Changho Suh. 4277-4288 [doi]
• SimplE Embedding for Link Prediction in Knowledge GraphsSeyed Mehran Kazemi, David Poole 0001. 4289-4300 [doi]
• Differentially Private Contextual Linear BanditsRoshan Shariff, Or Sheffet. 4301-4311 [doi]
• Submodular Field Grammars: Representation, Inference, and Application to Image ParsingAbram L. Friesen, Pedro M. Domingos. 4312-4322 [doi]
• A Bridging Framework for Model Optimization and Deep PropagationRisheng Liu, Shichao Cheng, Xiaokun Liu, Long Ma, Xin Fan, Zhongxuan Luo. 4323-4332 [doi]
• Completing State Representations using Spectral LearningNan Jiang, Alex Kulesza, Satinder P. Singh. 4333-4342 [doi]
• Optimization of Smooth Functions with Noisy Observations: Local Minimax RatesYining Wang, Sivaraman Balakrishnan, Aarti Singh. 4343-4354 [doi]
• Adding One Neuron Can Eliminate All Bad Local MinimaShiyu Liang, Ruoyu Sun, Jason D. Lee, R. Srikant. 4355-4365 [doi]
• Mean-field theory of graph neural networks in graph partitioningTatsuro Kawamoto, Masashi Tsubaki, Tomoyuki Obuchi. 4366-4376 [doi]
• The Physical Systems Behind Optimization AlgorithmsLin Yang, Raman Arora, Vladimir Braverman, Tuo Zhao. 4377-4386 [doi]
• Mallows Models for Top-k ListsFlavio Chierichetti, Anirban Dasgupta 0001, Shahrzad Haddadan, Ravi Kumar 0001, Silvio Lattanzi. 4387-4397 [doi]
• Amortized Inference RegularizationRui Shu, Hung H. Bui, Shengjia Zhao, Mykel J. Kochenderfer, Stefano Ermon. 4398-4407 [doi]
• Maximum Causal Tsallis Entropy Imitation LearningKyungjae Lee, Sungjoon Choi, Songhwai Oh. 4408-4418 [doi]
• Limited Memory Kelley's Method Converges for Composite Convex and Submodular ObjectivesSong Zhou, Swati Gupta, Madeleine Udell. 4419-4429 [doi]
• Semi-Supervised Learning with Declaratively Specified Entropy ConstraintsHaitian Sun, William W. Cohen, Lidong Bing. 4430-4440 [doi]
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended SystemsLinfeng Zhang, Jiequn Han, Han Wang, Wissam Saidi, Roberto Car, Weinan E. 4441-4451 [doi]
• Sparsified SGD with MemorySebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi. 4452-4463 [doi]
• Exponentiated Strongly Rayleigh DistributionsZelda E. Mariet, Suvrit Sra, Stefanie Jegelka. 4464-4474 [doi]
• Importance Weighting and Variational InferenceJustin Domke, Daniel R. Sheldon. 4475-4484 [doi]
• Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech SynthesisYe Jia, Yu Zhang, Ron J. Weiss, Quan Wang, Jonathan Shen, Fei Ren, Zhifeng Chen, Patrick Nguyen, Ruoming Pang, Ignacio Lopez-Moreno, Yonghui Wu. 4485-4495 [doi]
• Expanding Holographic Embeddings for Knowledge CompletionYexiang Xue, Yang Yuan, Zhitian Xu, Ashish Sabharwal. 4496-4506 [doi]
• Lifelong Inverse Reinforcement LearningJorge Armando Mendez Mendez, Shashank Shivkumar, Eric Eaton. 4507-4518 [doi]
• Explaining Deep Learning Models - A Bayesian Non-parametric ApproachWenbo Guo, Sui Huang, Yunzhe Tao, Xinyu Xing, Lin Lin. 4519-4529 [doi]
• Third-order Smoothness Helps: Faster Stochastic Optimization Algorithms for Finding Local MinimaYaodong Yu, Pan Xu, Quanquan Gu. 4530-4540 [doi]
• COLA: Decentralized Linear LearningLie He, An Bian, Martin Jaggi. 4541-4551 [doi]
• MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive HealthcareEdward Choi, Cao Xiao, Walter F. Stewart, Jimeng Sun. 4552-4562 [doi]
• Adaptive Sampling Towards Fast Graph Representation LearningWen-bing Huang, Tong Zhang 0001, Yu Rong, JunZhou Huang. 4563-4572 [doi]
• Hunting for Discriminatory Proxies in Linear Regression ModelsSamuel Yeom, Anupam Datta, Matt Fredrikson. 4573-4583 [doi]
• Towards Robust Detection of Adversarial ExamplesTianyu Pang, Chao Du, Yinpeng Dong, Jun Zhu. 4584-4594 [doi]
• Active MattingXin Yang, Ke Xu, Shaozhe Chen, Shengfeng He, Baocai Yin, Rynson W. H. Lau. 4595-4605 [doi]
• Learning filter widths of spectral decompositions with waveletsHaidar Khan, Bülent Yener. 4606-4617 [doi]
• Byzantine Stochastic Gradient DescentDan Alistarh, Zeyuan Allen Zhu, Jerry Li 0001. 4618-4628 [doi]
• PG-TS: Improved Thompson Sampling for Logistic Contextual BanditsBianca Dumitrascu, Karen Feng, Barbara E. Engelhardt. 4629-4638 [doi]
• Spectral Filtering for General Linear Dynamical SystemsElad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang. 4639-4648 [doi]
• On Learning Intrinsic Rewards for Policy Gradient MethodsZeyu Zheng, Junhyuk Oh, Satinder Singh. 4649-4659 [doi]
• Boolean Decision Rules via Column GenerationSanjeeb Dash, Oktay Günlük, Dennis Wei. 4660-4670 [doi]
• Adversarial Text Generation via Feature-Mover's DistanceLiqun Chen, Shuyang Dai, Chenyang Tao, Haichao Zhang, Zhe Gan, Dinghan Shen, Yizhe Zhang, Guoyin Wang, Ruiyi Zhang, Lawrence Carin. 4671-4682 [doi]
• Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound ConditionsMingrui Liu, Xiaoxuan Zhang, Lijun Zhang, Jing Rong, Tianbao Yang. 4683-4694 [doi]
• Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple KernelsShahin Shahrampour, Vahid Tarokh. 4695-4706 [doi]
• A Mathematical Model For Optimal Decisions In A Representative DemocracyMalik Magdon-Ismail, Lirong Xia. 4707-4716 [doi]
• Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-MakingNishant Desai, Andrew Critch, Stuart J. Russell. 4717-4725 [doi]
• Non-metric Similarity Graphs for Maximum Inner Product SearchStanislav Morozov, Artem Babenko. 4726-4735 [doi]
• Recurrently Controlled Recurrent NetworksYi Tay, Anh Tuan Luu, Siu Cheung Hui. 4736-4748 [doi]
• Fast greedy algorithms for dictionary selection with generalized sparsity constraintsKaito Fujii, Tasuku Soma. 4749-4758 [doi]
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics ModelsKurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine. 4759-4770 [doi]
• A Smoother Way to Train Structured Prediction ModelsVenkata Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui. 4771-4783 [doi]
• Context-dependent upper-confidence bounds for directed explorationRaksha Kumaraswamy, Matthew Schlegel, Adam White, Martha White. 4784-4794 [doi]
• A Unified View of Piecewise Linear Neural Network VerificationRudy R. Bunel, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, Pawan Kumar Mudigonda. 4795-4804 [doi]
• Hierarchical Graph Representation Learning with Differentiable PoolingZhitao Ying, Jiaxuan You, Christopher Morris 0001, Xiang Ren, William L. Hamilton, Jure Leskovec. 4805-4815 [doi]
• Non-Ergodic Alternating Proximal Augmented Lagrangian Algorithms with Optimal RatesQuoc Tran-Dinh. 4816-4824 [doi]
• Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer InterfacesBoyla Mainsah, Dmitry Kalika, Leslie M. Collins, Siyuan Liu, Chandra S. Throckmorton. 4825-4835 [doi]
• Porcupine Neural Networks: Approximating Neural Network LandscapesSoheil Feizi, Hamid Javadi, Jesse Zhang, David Tse. 4836-4846 [doi]
• Fairness Through Computationally-Bounded AwarenessMichael P. Kim, Omer Reingold, Guy N. Rothblum. 4847-4857 [doi]
• Adaptive Negative Curvature Descent with Applications in Non-convex OptimizationMingrui Liu, Zhe Li, Xiaoyu Wang, Jinfeng Yi, Tianbao Yang. 4858-4867 [doi]
• Is Q-Learning Provably Efficient?Chi Jin, Zeyuan Allen Zhu, Sébastien Bubeck, Michael I. Jordan. 4868-4878 [doi]
• Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic CorrectionsXin Zhang, Armando Solar-Lezama, Rishabh Singh. 4879-4890 [doi]
• Measures of distortion for machine learningLeena Chennuru Vankadara, Ulrike von Luxburg. 4891-4900 [doi]
• On the Local Minima of the Empirical RiskChi Jin, Lydia T. Liu, Rong Ge 0001, Michael I. Jordan. 4901-4910 [doi]
• Densely Connected Attention Propagation for Reading ComprehensionYi Tay, Anh Tuan Luu, Siu Cheung Hui, Jian Su. 4911-4922 [doi]
• Bandit Learning with Positive ExternalitiesVirag Shah, Jose Blanchet, Ramesh Johari. 4923-4933 [doi]
• Learning Confidence Sets using Support Vector MachinesWenbo Wang, Xingye Qiao. 4934-4943 [doi]
• Efficient Neural Network Robustness Certification with General Activation FunctionsHuan Zhang, Tsui-Wei Weng, Pin-Yu Chen, Cho-Jui Hsieh, Luca Daniel. 4944-4953 [doi]
• Hessian-based Analysis of Large Batch Training and Robustness to AdversariesZhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney. 4954-4964 [doi]
• Neural Edit Operations for Biological SequencesSatoshi Koide, Keisuke Kawano, Takuro Kutsuna. 4965-4975 [doi]
• Objective and efficient inference for couplings in neuronal networksYu Terada, Tomoyuki Obuchi, Takuya Isomura, Yoshiyuki Kabashima. 4976-4985 [doi]
• Learning from Group Comparisons: Exploiting Higher Order InteractionsYao Li, Minhao Cheng, Kevin Fujii, Fushing Hsieh, Cho-Jui Hsieh. 4986-4995 [doi]
• Supervising Unsupervised LearningVikas Garg. 4996-5006 [doi]
• Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risksQuan Zhang, Mingyuan Zhou. 5007-5018 [doi]
• Adversarially Robust Generalization Requires More DataLudwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry. 5019-5031 [doi]
• Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking AgentsEdoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth O. Stanley, Jeff Clune. 5032-5043 [doi]
• Practical exact algorithm for trembling-hand equilibrium refinements in gamesGabriele Farina, Nicola Gatti 0001, Tuomas Sandholm. 5044-5054 [doi]
• LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed LearningTianyi Chen, Georgios B. Giannakis, Tao Sun, Wotao Yin. 5055-5065 [doi]
• Scalable Robust Matrix Factorization with Nonconvex LossQuanming Yao, James T. Kwok. 5066-5075 [doi]
• Power-law efficient neural codes provide general link between perceptual bias and discriminabilityMichael Morais, Jonathan W. Pillow. 5076-5085 [doi]
• Geometry-Aware Recurrent Neural Networks for Active Visual RecognitionRicson Cheng, Ziyan Wang, Katerina Fragkiadaki. 5086-5096 [doi]
• Unsupervised Adversarial InvarianceAyush Jaiswal, Rex Yue Wu, Wael Abd-Almageed, Prem Natarajan. 5097-5107 [doi]
• Content preserving text generation with attribute controlsLajanugen Logeswaran, Honglak Lee, Samy Bengio. 5108-5118 [doi]
• Multi-armed Bandits with CompensationSiwei Wang, Longbo Huang. 5119-5128 [doi]
• GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN TrainingMingchao Yu, Zhifeng Lin, Krishna Narra, Songze Li, Youjie Li, Nam Sung Kim, Alexander G. Schwing, Murali Annavaram, Salman Avestimehr. 5129-5139 [doi]
• Learning in Games with Lossy FeedbackZhengyuan Zhou, Panayotis Mertikopoulos, Susan Athey, Nicholas Bambos, Peter W. Glynn, Yinyu Ye. 5140-5150 [doi]
• Scalable methods for 8-bit training of neural networksRon Banner, Itay Hubara, Elad Hoffer, Daniel Soudry. 5151-5159 [doi]
• Dropping Symmetry for Fast Symmetric Nonnegative Matrix FactorizationZhihui Zhu, Xiao Li, Kai Liu, Qiuwei Li. 5160-5170 [doi]
• Link Prediction Based on Graph Neural NetworksMuhan Zhang, Yixin Chen. 5171-5181 [doi]
• Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit taskDalin Guo, Angela J. Yu. 5182-5191 [doi]
• Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative ModelAaron Sidford, Mengdi Wang, Xian Wu, Lin Yang, Yinyu Ye. 5192-5202 [doi]
• ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise ConvolutionsHongyang Gao, Zhengyang Wang, Shuiwang Ji. 5203-5211 [doi]
• Causal Inference and Mechanism Clustering of A Mixture of Additive Noise ModelsShoubo Hu, Zhitang Chen, Vahid Partovi Nia, Lai-Wan Chan, Yanhui Geng. 5212-5222 [doi]
• Contour location via entropy reduction leveraging multiple information sourcesAlexandre Noll Marques, Rémi Lam, Karen Willcox. 5223-5233 [doi]
• Assessing Generative Models via Precision and RecallMehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet, Sylvain Gelly. 5234-5243 [doi]
• Multiple-Step Greedy Policies in Approximate and Online Reinforcement LearningYonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor. 5244-5253 [doi]
• A Convex Duality Framework for GANsFarzan Farnia, David Tse. 5254-5263 [doi]
• Horizon-Independent Minimax Linear RegressionAlan Malek, Peter L. Bartlett. 5264-5273 [doi]
• Exploiting Numerical Sparsity for Efficient Learning : Faster Eigenvector Computation and RegressionNeha Gupta, Aaron Sidford. 5274-5283 [doi]
• Experimental Design for Cost-Aware Learning of Causal GraphsErik M. Lindgren, Murat Kocaoglu, Alexandros G. Dimakis, Sriram Vishwanath. 5284-5294 [doi]
• Task-Driven Convolutional Recurrent Models of the Visual SystemAran Nayebi, Daniel Bear, Jonas Kubilius, Kohitij Kar, Surya Ganguli, David Sussillo, James J. DiCarlo, Daniel L. Yamins. 5295-5306 [doi]
• Meta-Reinforcement Learning of Structured Exploration StrategiesAbhishek Gupta, Russell Mendonca, Yuxuan Liu, Pieter Abbeel, Sergey Levine. 5307-5316 [doi]
• Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute ObservationTomoya Murata, Taiji Suzuki. 5317-5326 [doi]
• Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive VarianceNeal Jean, Sang Michael Xie, Stefano Ermon. 5327-5338 [doi]
• Generalizing to Unseen Domains via Adversarial Data AugmentationRiccardo Volpi, Hongseok Namkoong, Ozan Sener, John C. Duchi, Vittorio Murino, Silvio Savarese. 5339-5349 [doi]
• Hyperbolic Neural NetworksOctavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann. 5350-5360 [doi]
• Breaking the Curse of Horizon: Infinite-Horizon Off-Policy EstimationQiang Liu, Lihong Li 0001, Ziyang Tang, Dengyong Zhou. 5361-5371 [doi]
• Learning Task Specifications from DemonstrationsMarcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit A. Seshia. 5372-5382 [doi]
• Learning a latent manifold of odor representations from neural responses in piriform cortexAnqi Wu, Stan Pashkovski, Sandeep R. Datta, Jonathan W. Pillow. 5383-5393 [doi]
• Fully Understanding The Hashing TrickLior Kamma, Casper Benjamin Freksen, Kasper Green Larsen. 5394-5404 [doi]
• Evolved Policy GradientsRein Houthooft, Yuhua Chen, Phillip Isola, Bradly C. Stadie, Filip Wolski, Jonathan Ho, Pieter Abbeel. 5405-5414 [doi]
• The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural NetworkJeffrey Pennington, Pratik Worah. 5415-5424 [doi]
• Learning Concave Conditional Likelihood Models for Improved Analysis of Tandem Mass SpectraJohn T. Halloran, David M. Rocke. 5425-5435 [doi]
• Differentially Private k-Means with Constant Multiplicative ErrorUri Stemmer, Haim Kaplan. 5436-5446 [doi]
• Policy Optimization via Importance SamplingAlberto Maria Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli. 5447-5459 [doi]
• Estimating Learnability in the Sublinear Data RegimeWeihao Kong, Gregory Valiant. 5460-5469 [doi]
• Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian OptimisationShivapratap Gopakumar, Sunil Gupta, Santu Rana, Vu Nguyen 0001, Svetha Venkatesh. 5470-5478 [doi]
• Community Exploration: From Offline Optimization to Online LearningXiaowei Chen, Weiran Huang, Wei Chen, John C. S. Lui. 5479-5488 [doi]
• A Dual Framework for Low-rank Tensor CompletionMadhav Nimishakavi, Pratik Kumar Jawanpuria, Bamdev Mishra. 5489-5500 [doi]
• Low-rank Interaction with Sparse Additive Effects Model for Large Data FramesGeneviève Robin, Hoi-To Wai, Julie Josse, Olga Klopp, Eric Moulines. 5501-5511 [doi]
• Inference Aided Reinforcement Learning for Incentive Mechanism Design in CrowdsourcingZehong Hu, Yitao Liang, Jie Zhang, Zhao Li, Yang Liu. 5512-5522 [doi]
• Middle-Out DecodingShikib Mehri, Leonid Sigal. 5523-5534 [doi]
• First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear TimeYi Xu, Jing Rong, Tianbao Yang. 5535-5545 [doi]
• To Trust Or Not To Trust A ClassifierHeinrich Jiang, Been Kim, Melody Y. Guan, Maya R. Gupta. 5546-5557 [doi]
• Reparameterization Gradient for Non-differentiable ModelsWonyeol Lee 0001, Hangyeol Yu, Hongseok Yang. 5558-5568 [doi]
• A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex OptimizationZhize Li, Jian Li. 5569-5579 [doi]
• Multimodal Generative Models for Scalable Weakly-Supervised LearningMike Wu, Noah Goodman. 5580-5590 [doi]
• How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?Richard Y. Zhang, Cédric Josz, Somayeh Sojoudi, Javad Lavaei. 5591-5602 [doi]
• Occam's razor is insufficient to infer the preferences of irrational agentsStuart Armstrong, Sören Mindermann. 5603-5614 [doi]
• Manifold Structured PredictionAlessandro Rudi, Carlo Ciliberto, Gian Maria Marconi, Lorenzo Rosasco. 5615-5626 [doi]
• Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation DiversityLaming Chen, Guoxin Zhang, Eric Zhou. 5627-5638 [doi]
• Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPsYanlin Han, Piotr J. Gmytrasiewicz. 5639-5647 [doi]
• Contextual Pricing for Lipschitz BuyersJieming Mao, Renato Paes Leme, Jon Schneider. 5648-5656 [doi]
• Online Improper Learning with an Approximation OracleElad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li. 5657-5665 [doi]
• Bandit Learning in Concave N-Person GamesMario Bravo, David S. Leslie, Panayotis Mertikopoulos. 5666-5676 [doi]
• On Fast Leverage Score Sampling and Optimal LearningAlessandro Rudi, Daniele Calandriello, Luigi Carratino, Lorenzo Rosasco. 5677-5687 [doi]
• Unsupervised Video Object Segmentation for Deep Reinforcement LearningVikash Goel, Jameson Weng, Pascal Poupart. 5688-5699 [doi]
• Efficient inference for time-varying behavior during learningNicholas G. Roy, Ji Hyun Bak, Athena Akrami, Carlos Brody, Jonathan W. Pillow. 5700-5710 [doi]
• Learning convex polytopes with marginLee-Ad Gottlieb, Eran Kaufman, Aryeh Kontorovich, Gabriel Nivasch. 5711-5721 [doi]
• Critical initialisation for deep signal propagation in noisy rectifier neural networksArnu Pretorius, Elan Van Biljon, Steve Kroon, Herman Kamper. 5722-5731 [doi]
• Insights on representational similarity in neural networks with canonical correlationAri S. Morcos, Maithra Raghu, Samy Bengio. 5732-5741 [doi]
• Variational Inference with Tail-adaptive f-DivergenceDilin Wang, Hao Liu, Qiang Liu. 5742-5752 [doi]
• Mental Sampling in Multimodal RepresentationsJian-Qiao Zhu, Adam Sanborn, Nick Chater. 5753-5764 [doi]
• Adversarially Robust Optimization with Gaussian ProcessesIlija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher. 5765-5775 [doi]
• Learning to MultitaskYu Zhang, Ying Wei, Qiang Yang. 5776-5787 [doi]
• Loss Functions for Multiset PredictionSean Welleck, Zixin Yao, Yu Gai, Jialin Mao, Zheng Zhang, KyungHyun Cho. 5788-5797 [doi]
• Computing Kantorovich-Wasserstein Distances on d-dimensional histograms using (d+1)-partite graphsGennaro Auricchio, Federico Bassetti, Stefano Gualandi, Marco Veneroni. 5798-5808 [doi]
• Neural Interaction Transparency (NIT): Disentangling Learned Interactions for Improved InterpretabilityMichael Tsang, Hanpeng Liu, Sanjay Purushotham, Pavankumar Murali, Yan Liu. 5809-5818 [doi]
• CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule SubspacesLiheng Zhang, Marzieh Edraki, Guo-Jun Qi. 5819-5828 [doi]
• Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata InfluenceTrong Dinh Thac Do, Longbing Cao. 5829-5840 [doi]
• Masking: A New Perspective of Noisy SupervisionBo Han, Jiangchao Yao, Gang Niu, Mingyuan Zhou, Ivor W. Tsang, Ya Zhang, Masashi Sugiyama. 5841-5851 [doi]
• On GANs and GMMsEitan Richardson, Yair Weiss. 5852-5863 [doi]
• Differential Properties of Sinkhorn Approximation for Learning with Wasserstein DistanceGiulia Luise, Alessandro Rudi, Massimiliano Pontil, Carlo Ciliberto. 5864-5874 [doi]
• Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matchingStepan Tulyakov, Anton Ivanov, François Fleuret. 5875-5885 [doi]
• A Bayes-Sard Cubature MethodToni Karvonen, Chris J. Oates, Simo Särkkä. 5886-5897 [doi]
• Dual Swap DisentanglingZunlei Feng, Xinchao Wang, Chenglong Ke, Anxiang Zeng, Dacheng Tao, Mingli Song. 5898-5908 [doi]
• Diverse Ensemble Evolution: Curriculum Data-Model MarriageTianyi Zhou, Shengjie Wang, Jeff A. Bilmes. 5909-5920 [doi]
• Binary Classification from Positive-Confidence DataTakashi Ishida, Gang Niu, Masashi Sugiyama. 5921-5932 [doi]
• Deep Generative Models for Distribution-Preserving Lossy CompressionMichael Tschannen, Eirikur Agustsson, Mario Lucic. 5933-5944 [doi]
• Exact natural gradient in deep linear networks and its application to the nonlinear caseAlberto Bernacchia, Máté Lengyel, Guillaume Hennequin. 5945-5954 [doi]
• Constructing Fast Network through Deconstruction of ConvolutionYunho Jeon, Junmo Kim. 5955-5965 [doi]
• Memory Replay GANs: Learning to Generate New Categories without ForgettingChenshen Wu, Luis Herranz, Xialei Liu, Yaxing Wang, Joost van de Weijer, Bogdan Raducanu. 5966-5976 [doi]
• The Convergence of Sparsified Gradient MethodsDan Alistarh, Torsten Hoefler, Mikael Johansson 0001, Nikola Konstantinov, Sarit Khirirat, Cédric Renggli. 5977-5987 [doi]
• Automating Bayesian optimization with Bayesian optimizationGustavo Malkomes, Roman Garnett. 5988-5997 [doi]
• Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot LearningYunlong Yu, Zhong Ji, Yanwei Fu, Jichang Guo, Yanwei Pang, Zhongfei (Mark) Zhang. 5998-6007 [doi]
• Dirichlet-based Gaussian Processes for Large-scale Calibrated ClassificationDimitrios Milios, Raffaello Camoriano, Pietro Michiardi, Lorenzo Rosasco, Maurizio Filippone. 6008-6018 [doi]
• Multi-Task Zipping via Layer-wise Neuron SharingXiaoxi He, Zimu Zhou, Lothar Thiele. 6019-6029 [doi]
• Dimensionally Tight Bounds for Second-Order Hamiltonian Monte CarloOren Mangoubi, Nisheeth K. Vishnoi. 6030-6040 [doi]
• Approximation algorithms for stochastic clusteringDavid G. Harris, Shi Li, Aravind Srinivasan, Khoa Trinh, Thomas Pensyl. 6041-6050 [doi]
• Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural NetworksXiaodong Cui, Wei Zhang, Zoltán Tüske, Michael Picheny. 6051-6061 [doi]
• Learning to Infer Graphics Programs from Hand-Drawn ImagesKevin Ellis, Daniel Ritchie, Armando Solar-Lezama, Josh Tenenbaum. 6062-6071 [doi]
• Graphical Generative Adversarial NetworksChongxuan Li, Max Welling, Jun Zhu 0001, Bo Zhang. 6072-6083 [doi]
• Variational Learning on Aggregate Outputs with Gaussian ProcessesHo Chung Leon Law, Dino Sejdinovic, Ewan Cameron, Tim C. D. Lucas, Seth R. Flaxman, Katherine Battle, Kenji Fukumizu. 6084-6094 [doi]
• MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence ModelsBoyuan Pan, Yazheng Yang, Hao Li, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He. 6095-6105 [doi]
• Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural NetworksAli Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras, Tom Goldstein. 6106-6116 [doi]
• Information Constraints on Auto-Encoding Variational BayesRomain Lopez, Jeffrey Regier, Michael I. Jordan, Nir Yosef. 6117-6128 [doi]
• Recurrent Transformer Networks for Semantic CorrespondenceSeungryong Kim, Stephen Lin, Sangryul Jeon, Dongbo Min, Kwanghoon Sohn. 6129-6139 [doi]
• Online convex optimization for cumulative constraintsJianjun Yuan, Andrew G. Lamperski. 6140-6149 [doi]
• Predict Responsibly: Improving Fairness and Accuracy by Learning to DeferDavid Madras, Toniann Pitassi, Richard S. Zemel. 6150-6160 [doi]
• Deep State Space Models for Unconditional Word GenerationFlorian Schmidt, Thomas Hofmann. 6161-6171 [doi]
• ResNet with one-neuron hidden layers is a Universal ApproximatorHongzhou Lin, Stefanie Jegelka. 6172-6181 [doi]
• Transfer of Value Functions via Variational MethodsAndrea Tirinzoni, Rafael Rodríguez-Sánchez, Marcello Restelli. 6182-6192 [doi]
• The Cluster Description Problem - Complexity Results, Formulations and ApproximationsIan Davidson, Antoine Gourru, S. S. Ravi. 6193-6203 [doi]
• Sharp Bounds for Generalized Uniformity TestingIlias Diakonikolas, Daniel M. Kane, Alistair Stewart. 6204-6213 [doi]
• Deep Neural Networks with Box ConvolutionsEgor Burkov, Victor S. Lempitsky. 6214-6224 [doi]
• Learning towards Minimum Hyperspherical EnergyWeiyang Liu, Rongmei Lin, Zhen Liu, Lixin Liu, Zhiding Yu, Bo Dai, Le Song. 6225-6236 [doi]
• LF-Net: Learning Local Features from ImagesYuki Ono, Eduard Trulls, Pascal Fua, Kwang Moo Yi. 6237-6247 [doi]
• SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural GradientAaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark W. Schmidt, Mohammad Emtiyaz Khan. 6248-6258 [doi]
• Tangent: Automatic differentiation using source-code transformation for dynamically typed array programmingBart van Merrienboer, Dan Moldovan, Alexander B. Wiltschko. 6259-6268 [doi]
• Multi-domain Causal Structure Learning in Linear SystemsAmirEmad Ghassami, Negar Kiyavash, Biwei Huang, Kun Zhang. 6269-6279 [doi]
• Privacy Amplification by Subsampling: Tight Analyses via Couplings and DivergencesBorja Balle, Gilles Barthe, Marco Gaboardi. 6280-6290 [doi]
• Exponentially Weighted Imitation Learning for Batched Historical DataQing Wang, Jiechao Xiong, Lei Han, Peng Sun, Han Liu, Tong Zhang. 6291-6300 [doi]
• Algebraic tests of general Gaussian latent tree modelsDennis Leung, Mathias Drton. 6301-6310 [doi]
• Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language ModelsMinjia Zhang, Wenhan Wang, Xiaodong Liu, Jianfeng Gao, Yuxiong He. 6311-6322 [doi]
• Deep Structured Prediction with Nonlinear Output TransformationsColin Graber, Ofer Meshi, Alexander G. Schwing. 6323-6334 [doi]
• Sequential Test for the Lowest Mean: From Thompson to Murphy SamplingEmilie Kaufmann, Wouter M. Koolen, Aurélien Garivier. 6335-6345 [doi]
• Distributed Learning without Distress: Privacy-Preserving Empirical Risk MinimizationBargav Jayaraman, Lingxiao Wang, David Evans 0001, Quanquan Gu. 6346-6357 [doi]
• A no-regret generalization of hierarchical softmax to extreme multi-label classificationMarek Wydmuch, Kalina Jasinska, Mikhail Kuznetsov, Róbert Busa-Fekete, Krzysztof Dembczynski. 6358-6368 [doi]
• Efficient Formal Safety Analysis of Neural NetworksShiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana. 6369-6379 [doi]
• Bayesian Distributed Stochastic Gradient DescentMichael Teng, Frank Wood. 6380-6390 [doi]
• Visualizing the Loss Landscape of Neural NetsHao Li, Zheng Xu 0002, Gavin Taylor, Christoph Studer, Tom Goldstein. 6391-6401 [doi]
• The Limits of Post-Selection GeneralizationJonathan Ullman, Adam D. Smith, Kobbi Nissim, Uri Stemmer, Thomas Steinke. 6402-6411 [doi]
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph GenerationJiaxuan You, Bowen Liu, Zhitao Ying, Vijay S. Pande, Jure Leskovec. 6412-6422 [doi]
• On Controllable Sparse Alternatives to SoftmaxAnirban Laha, Saneem Ahmed Chemmengath, Priyanka Agrawal, Mitesh M. Khapra, Karthik Sankaranarayanan, Harish G. Ramaswamy. 6423-6433 [doi]
• L4: Practical loss-based stepsize adaptation for deep learningMichal Rolinek, Georg Martius. 6434-6444 [doi]
• Learning Latent Subspaces in Variational AutoencodersJack Klys, Jake Snell, Richard S. Zemel. 6445-6455 [doi]
• Turbo Learning for CaptionBot and DrawingBotQiuyuan Huang, Pengchuan Zhang, Dapeng Oliver Wu, Lei Zhang. 6456-6466 [doi]
• Learning to Teach with Dynamic Loss FunctionsLijun Wu, Fei Tian, Yingce Xia, Yang Fan, Tao Qin, Jian-Huang Lai, Tie-Yan Liu. 6467-6478 [doi]
• Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object RepresentationEdward Smith, Scott Fujimoto, David Meger. 6479-6489 [doi]
• Size-Noise Tradeoffs in Generative NetworksBolton Bailey, Matus J. Telgarsky. 6490-6500 [doi]
• Online Adaptive Methods, Universality and AccelerationKfir Yehuda Levy, Alp Yurtsever, Volkan Cevher. 6501-6510 [doi]
• Compact Generalized Non-local NetworkKaiyu Yue, Ming Sun, Yuchen Yuan, Feng Zhou, Errui Ding, Fuxin Xu. 6511-6520 [doi]
• On the Local Hessian in Back-propagationHuishuai Zhang, Wei Chen 0034, Tie-Yan Liu. 6521-6531 [doi]
• The Everlasting Database: Statistical Validity at a Fair PriceBlake E. Woodworth, Vitaly Feldman, Saharon Rosset, Nati Srebro. 6532-6541 [doi]
• Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural NetworksYusuke Tsuzuku, Issei Sato, Masashi Sugiyama. 6542-6551 [doi]
• Proximal SCOPE for Distributed Sparse LearningShen-Yi Zhao, Gong-Duo Zhang, Ming-Wei Li, Wu-Jun Li. 6552-6561 [doi]
• On Coresets for Logistic RegressionAlexander Munteanu, Chris Schwiegelshohn, Christian Sohler, David P. Woodruff. 6562-6571 [doi]
• Neural Ordinary Differential EquationsTian Qi Chen, Yulia Rubanova, Jesse Bettencourt, David K. Duvenaud. 6572-6583 [doi]
• Unsupervised Learning of Artistic Styles with Archetypal Style AnalysisDaan Wynen, Cordelia Schmid, Julien Mairal. 6584-6593 [doi]
• Approximating Real-Time Recurrent Learning with Random Kronecker FactorsAsier Mujika, Florian Meier, Angelika Steger. 6594-6603 [doi]
• Contamination Attacks and Mitigation in Multi-Party Machine LearningJamie Hayes, Olga Ohrimenko. 6604-6616 [doi]
• An Improved Analysis of Alternating Minimization for Structured Multi-Response RegressionSheng Chen, Arindam Banerjee. 6617-6628 [doi]
• Incorporating Context into Language Encoding Models for fMRIShailee Jain, Alexander Huth. 6629-6638 [doi]
• CatBoost: unbiased boosting with categorical featuresLiudmila Ostroumova Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, Andrey Gulin. 6639-6649 [doi]
• Query K-means Clustering and the Double Dixie Cup ProblemI Chien, Chao Pan, Olgica Milenkovic. 6650-6659 [doi]
• Training Neural Networks Using Features ReplayZhouyuan Huo, Bin Gu, Heng Huang. 6660-6669 [doi]
• Modeling Dynamic Missingness of Implicit Feedback for RecommendationMenghan Wang, Mingming Gong, Xiaolin Zheng, Kun Zhang. 6670-6679 [doi]
• Representation Learning of Compositional DataMarta Avalos, Richard Nock, Cheng Soon Ong, Julien Rouar, Ke Sun. 6680-6690 [doi]
• Model-based targeted dimensionality reduction for neuronal population dataMikio Aoi, Jonathan W. Pillow. 6691-6700 [doi]
• On gradient regularizers for MMD GANsMichael Arbel, Dougal J. Sutherland, Mikolaj Binkowski, Arthur Gretton. 6701-6711 [doi]
• Heterogeneous Multi-output Gaussian Process PredictionPablo Moreno-Muñoz, Antonio Artés-Rodríguez, Mauricio A. Álvarez. 6712-6721 [doi]
• Large-Scale Stochastic Sampling from the Probability SimplexJack Baker, Paul Fearnhead, Emily B. Fox, Christopher Nemeth. 6722-6732 [doi]
• Policy Regret in Repeated GamesRaman Arora, Michael Dinitz, Teodor Vanislavov Marinov, Mehryar Mohri. 6733-6742 [doi]
• A Theory-Based Evaluation of Nearest Neighbor Models Put Into PracticeHendrik Fichtenberger, Dennis Rohde. 6743-6754 [doi]
• Banach Wasserstein GANJonas Adler, Sebastian Lunz. 6755-6764 [doi]
• Provable Gaussian Embedding with One ObservationMing Yu, Zhuoran Yang, Tuo Zhao, Mladen Kolar, Zhaoran Wang. 6765-6775 [doi]
• BRITS: Bidirectional Recurrent Imputation for Time SeriesWei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, Yitan Li. 6776-6786 [doi]
• M-Walk: Learning to Walk over Graphs using Monte Carlo Tree SearchYelong Shen, Jianshu Chen, Po-Sen Huang, Yuqing Guo, Jianfeng Gao. 6787-6798 [doi]
• Extracting Relationships by Multi-Domain MatchingYitong Li, michael Murias, Geraldine Dawson, David E. Carlson. 6799-6810 [doi]
• Efficient Gradient Computation for Structured Output Learning with Rational and Tropical LossesCorinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Dmitry Storcheus, Scott Yang. 6811-6822 [doi]
• Generative Probabilistic Novelty Detection with Adversarial AutoencodersStanislav Pidhorskyi, Ranya Almohsen, Gianfranco Doretto. 6823-6834 [doi]
• Diminishing Returns Shape Constraints for Interpretability and RegularizationMaya R. Gupta, Dara Bahri, Andrew Cotter, Kevin Robert Canini. 6835-6845 [doi]
• Scalable Hyperparameter Transfer LearningValerio Perrone, Rodolphe Jenatton, Matthias W. Seeger, Cédric Archambeau. 6846-6856 [doi]
• Stochastic Nonparametric Event-Tensor DecompositionShandian Zhe, Yishuai Du. 6857-6867 [doi]
• Scaling Gaussian Process Regression with DerivativesDavid Eriksson, Kun Dong, Eric Hans Lee, David Bindel, Andrew Gordon Wilson. 6868-6878 [doi]
• Differentially Private Testing of Identity and Closeness of Discrete DistributionsJayadev Acharya, Ziteng Sun, Huanyu Zhang. 6879-6891 [doi]
• Bayesian Adversarial LearningNanyang Ye, Zhanxing Zhu. 6892-6901 [doi]
• Efficient Convex Completion of Coupled Tensors using Coupled Nuclear NormsKishan Wimalawarne, Hiroshi Mamitsuka. 6902-6910 [doi]
• Maximizing Induced Cardinality Under a Determinantal Point ProcessJennifer A. Gillenwater, Alex Kulesza, Sergei Vassilvitskii, Zelda E. Mariet. 6911-6920 [doi]
• Causal Inference with Noisy and Missing Covariates via Matrix FactorizationNathan Kallus, Xiaojie Mao, Madeleine Udell. 6921-6932 [doi]
• rho-POMDPs have Lipschitz-Continuous epsilon-Optimal Value FunctionsMathieu Fehr, Olivier Buffet, Vincent Thomas, Jilles Steeve Dibangoye. 6933-6943 [doi]
• Online Structure Learning for Feed-Forward and Recurrent Sum-Product NetworksAgastya Kalra, Abdullah Rashwan, Wei-Shou Hsu, Pascal Poupart, Prashant Doshi, Georgios Trimponias. 6944-6954 [doi]
• Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One LossStephen Mussmann, Percy S. Liang. 6955-6964 [doi]
• A Probabilistic U-Net for Segmentation of Ambiguous ImagesSimon Kohl, Bernardino Romera-Paredes, Clemens Meyer, Jeffrey De Fauw, Joseph R. Ledsam, Klaus H. Maier-Hein, S. M. Ali Eslami, Danilo Jimenez Rezende, Olaf Ronneberger. 6965-6975 [doi]
• Unorganized Malicious Attacks DetectionMing Pang, Wei Gao 0008, Min Tao, Zhi-Hua Zhou. 6976-6985 [doi]
• Causal Inference via Kernel Deviance MeasuresJovana Mitrovic, Dino Sejdinovic, Yee Whye Teh. 6986-6994 [doi]
• Bayesian Alignments of Warped Multi-Output Gaussian ProcessesMarkus Kaiser, Clemens Otte, Thomas A. Runkler, Carl Henrik Ek. 6995-7004 [doi]
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural NetworksYingyezhe Jin, Wenrui Zhang, Peng Li. 7005-7015 [doi]
• Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector ComputationKush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan. 7016-7025 [doi]
• Efficient online algorithms for fast-rate regret bounds under sparsityPierre Gaillard, Olivier Wintenberger. 7026-7036 [doi]
• GILBO: One Metric to Measure Them AllAlexander A. Alemi, Ian Fischer. 7037-7046 [doi]
• Predictive Uncertainty Estimation via Prior NetworksAndrey Malinin, Mark J. F. Gales. 7047-7058 [doi]
• Dual Policy IterationWen Sun 0002, Geoffrey J. Gordon, Byron Boots, J. Andrew Bagnell. 7059-7069 [doi]
• A probabilistic population code based on neural samplesSabyasachi Shivkumar, Richard Lange, Ankani Chattoraj, Ralf Haefner. 7070-7079 [doi]
• Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural NetworksAnirvan M. Sengupta, Cengiz Pehlevan, Mariano Tepper, Alexander Genkin, Dmitri B. Chklovskii. 7080-7090 [doi]
• On the Convergence and Robustness of Training GANs with Regularized Optimal TransportMaziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee. 7091-7101 [doi]
• Model-Agnostic Private LearningRaef Bassily, Abhradeep Guha Thakurta, Om Dipakbhai Thakkar. 7102-7112 [doi]
• Constrained Generation of Semantically Valid Graphs via Regularizing Variational AutoencodersTengfei Ma, Jie Chen, Cao Xiao. 7113-7124 [doi]
• Provably Correct Automatic Sub-Differentiation for Qualified ProgramsSham M. Kakade, Jason D. Lee. 7125-7135 [doi]
• Deep Homogeneous Mixture Models: Representation, Separation, and ApproximationPriyank Jaini, Pascal Poupart, Yaoliang Yu. 7136-7145 [doi]
• Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networksGrant M. Rotskoff, Eric Vanden-Eijnden. 7146-7155 [doi]
• Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask DependenciesSungryull Sohn, Junhyuk Oh, Honglak Lee. 7156-7166 [doi]
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial AttacksKimin Lee, Kibok Lee, Honglak Lee, Jinwoo Shin. 7167-7177 [doi]
• End-to-End Differentiable Physics for Learning and ControlFilipe de Avila Belbute-Peres, Kevin A. Smith, Kelsey Allen, Josh Tenenbaum, J. Zico Kolter. 7178-7189 [doi]
• BRUNO: A Deep Recurrent Model for Exchangeable DataIryna Korshunova, Jonas Degrave, Ferenc Huszar, Yarin Gal, Arthur Gretton, Joni Dambre. 7190-7198 [doi]
• Stimulus domain transfer in recurrent models for large scale cortical population prediction on videoFabian H. Sinz, Alexander S. Ecker, Paul G. Fahey, Edgar Y. Walker, Erick Cobos, Emmanouil Froudarakis, Dimitri Yatsenko, Zachary Pitkow, Jacob Reimer, Andreas S. Tolias. 7199-7210 [doi]
• Mapping Images to Scene Graphs with Permutation-Invariant Structured PredictionRoei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant, Amir Globerson. 7211-7221 [doi]
• Distributed Multi-Player Bandits - a Game of Thrones ApproachIlai Bistritz, Amir Leshem. 7222-7232 [doi]
• Efficient Loss-Based Decoding on Graphs for Extreme ClassificationItay Evron, Edward Moroshko, Koby Crammer. 7233-7244 [doi]
• Chaining Mutual Information and Tightening Generalization BoundsAmir R. Asadi, Emmanuel Abbe, Sergio Verdú. 7245-7254 [doi]
• Implicit Probabilistic Integrators for ODEsOnur Teymur, Han Cheng Lie, Tim Sullivan, Ben Calderhead. 7255-7264 [doi]
• Learning Attentional Communication for Multi-Agent CooperationJiechuan Jiang, Zongqing Lu. 7265-7275 [doi]
• Training Deep Models Faster with Robust, Approximate Importance SamplingTyler B. Johnson, Carlos Guestrin. 7276-7286 [doi]
• Bandit Learning with Implicit FeedbackYi Qi, Qingyun Wu, Hongning Wang, Jie Tang 0001, Maosong Sun. 7287-7297 [doi]
• Unsupervised Text Style Transfer using Language Models as DiscriminatorsZichao Yang, Zhiting Hu, Chris Dyer, Eric P. Xing, Taylor Berg-Kirkpatrick. 7298-7309 [doi]
• Relational recurrent neural networksAdam Santoro, Ryan Faulkner, David Raposo, Jack W. Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy P. Lillicrap. 7310-7321 [doi]
• Streaming Kernel PCA with \tilde{O}(\sqrt{n}) Random FeaturesEnayat Ullah, Poorya Mianjy, Teodor Vanislavov Marinov, Raman Arora. 7322-7332 [doi]
• REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease DiagnosisYu-Shao Peng, Kai-Fu Tang, Hsuan-Tien Lin, Edward Y. Chang. 7333-7342 [doi]
• Bayesian Model-Agnostic Meta-LearningJaesik Yoon, Taesup Kim, Ousmane Dia, Sungwoong Kim, Yoshua Bengio, Sungjin Ahn. 7343-7353 [doi]
• Disconnected Manifold Learning for Generative Adversarial NetworksMahyar Khayatkhoei, Maneesh Kumar Singh, Ahmed Elgammal. 7354-7364 [doi]
• Unsupervised Cross-Modal Alignment of Speech and Text Embedding SpacesYu-An Chung, Wei-Hung Weng, Schrasing Tong, James Glass. 7365-7375 [doi]
• Learning Signed Determinantal Point Processes through the Principal Minor Assignment ProblemVictor-Emmanuel Brunel. 7376-7385 [doi]
• Out-of-Distribution Detection using Multiple Semantic Label RepresentationsGabi Shalev, Yossi Adi, Joseph Keshet. 7386-7396 [doi]
• Stochastic Chebyshev Gradient Descent for Spectral OptimizationInsu Han, Haim Avron, Jinwoo Shin. 7397-7407 [doi]
• Revisiting (\epsilon, \gamma, \tau)-similarity learning for domain adaptationSofiane Dhouib, Ievgen Redko. 7408-7417 [doi]
• How to tell when a clustering is (approximately) correct using convex relaxationsMarina Meila. 7418-7429 [doi]
• Constant Regret, Generalized Mixability, and Mirror DescentZakaria Mhammedi, Robert C. Williamson. 7430-7439 [doi]
• A Bayesian Approach to Generative Adversarial Imitation LearningWonseok Jeon, Seokin Seo, Kee-Eung Kim. 7440-7450 [doi]
• Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous AnalysisAlyson K. Fletcher, Parthe Pandit, Sundeep Rangan, Subrata Sarkar, Philip Schniter. 7451-7460 [doi]
• Constrained Cross-Entropy Method for Safe Reinforcement LearningMin Wen, Ufuk Topcu. 7461-7471 [doi]
• Multi-Agent Generative Adversarial Imitation LearningJiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon. 7472-7483 [doi]
• Adaptive Learning with Unknown Information FlowsYonatan Gur, Ahmadreza Momeni. 7484-7493 [doi]
• Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural NetworksBryan Lim. 7494-7504 [doi]
• Generative modeling for protein structuresNamrata Anand, Possu Huang. 7505-7516 [doi]
• Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte CarloMarton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes. 7517-7527 [doi]
• Knowledge Distillation by On-the-Fly Native EnsembleXu Lan, Xiatian Zhu, Shaogang Gong. 7528-7538 [doi]
• Non-Adversarial Mapping with VAEsYedid Hoshen. 7539-7548 [doi]
• Generalisation in humans and deep neural networksRobert Geirhos, Carlos R. Medina Temme, Jonas Rauber, Heiko H. Schütt, Matthias Bethge, Felix A. Wichmann. 7549-7561 [doi]
• Towards Text Generation with Adversarially Learned Neural OutlinesSandeep Subramanian, Sai Rajeswar, Alessandro Sordoni, Adam Trischler, Aaron C. Courville, Chris Pal. 7562-7574 [doi]
• cpSGD: Communication-efficient and differentially-private distributed SGDNaman Agarwal, Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, Brendan McMahan. 7575-7586 [doi]
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU AccelerationJacob R. Gardner, Geoff Pleiss, Kilian Q. Weinberger, David Bindel, Andrew Gordon Wilson. 7587-7597 [doi]
• Diffusion Maps for Textual Network EmbeddingXinyuan Zhang, Yitong Li, Dinghan Shen, Lawrence Carin. 7598-7608 [doi]
• Simple, Distributed, and Accelerated Probabilistic ProgrammingDustin Tran, Matthew D. Hoffman, Dave Moore, Christopher Suter, Srinivas Vasudevan, Alexey Radul. 7609-7620 [doi]
• VideoCapsuleNet: A Simplified Network for Action DetectionKevin Duarte, Yogesh Singh Rawat, Mubarak Shah. 7621-7630 [doi]
• Rectangular Bounding ProcessXuhui Fan, Bin Li, Scott Sisson. 7631-7641 [doi]
• Improved Algorithms for Collaborative PAC LearningHuy L. Nguyen, Lydia Zakynthinou. 7642-7650 [doi]
• Sparse Attentive Backtracking: Temporal Credit Assignment Through RemindingNan Rosemary Ke, Anirudh Goyal, Olexa Bilaniuk, Jonathan Binas, Michael C. Mozer, Chris Pal, Yoshua Bengio. 7651-7662 [doi]
• Communication Compression for Decentralized TrainingHanlin Tang, Shaoduo Gan, Ce Zhang, Tong Zhang, Ji Liu. 7663-7673 [doi]
• Depth-Limited Solving for Imperfect-Information GamesNoam Brown, Tuomas Sandholm, Brandon Amos. 7674-7685 [doi]
• Training Deep Neural Networks with 8-bit Floating Point NumbersNaigang Wang, Jungwook Choi, Daniel Brand, Chia-Yu Chen, Kailash Gopalakrishnan. 7686-7695 [doi]
• Scalar Posterior Sampling with ApplicationsGeorgios Theocharous, Zheng Wen, Yasin Abbasi, Nikos Vlassis. 7696-7704 [doi]
• Understanding Batch NormalizationNils Bjorck, Carla P. Gomes, Bart Selman, Kilian Q. Weinberger. 7705-7716 [doi]
• Adversarial Scene Editing: Automatic Object Removal from Weak SupervisionRakshith Shetty, Mario Fritz, Bernt Schiele. 7717-7727 [doi]
• Attacks Meet Interpretability: Attribute-steered Detection of Adversarial SamplesGuanhong Tao, ShiQing Ma, Yingqi Liu, Xiangyu Zhang. 7728-7739 [doi]
• On Neuronal CapacityPierre Baldi, Roman Vershynin. 7740-7749 [doi]
• Breaking the Activation Function Bottleneck through Adaptive ParameterizationSebastian Flennerhag, Hujun Yin, John A. Keane, Mark Elliot. 7750-7761 [doi]
• Learning Loop Invariants for Program VerificationXujie Si, Hanjun Dai, Mukund Raghothaman, Mayur Naik, Le Song. 7762-7773 [doi]
• Cooperative Learning of Audio and Video Models from Self-Supervised SynchronizationBruno Korbar, Du Tran, Lorenzo Torresani. 7774-7785 [doi]
• Towards Robust Interpretability with Self-Explaining Neural NetworksDavid Alvarez-Melis, Tommi S. Jaakkola. 7786-7795 [doi]
• Deep State Space Models for Time Series ForecastingSyama Sundar Rangapuram, Matthias W. Seeger, Jan Gasthaus, Lorenzo Stella, Yuyang Wang, Tim Januschowski. 7796-7805 [doi]
• Constrained Graph Variational Autoencoders for Molecule DesignQi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander L. Gaunt. 7806-7815 [doi]
• Learning Libraries of Subroutines for Neurally-Guided Bayesian Program InductionKevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama, Josh Tenenbaum. 7816-7826 [doi]
• Neural Architecture OptimizationRenqian Luo, Fei Tian, Tao Qin, Enhong Chen, Tie-Yan Liu. 7827-7838 [doi]
• Preference Based Adaptation for Learning ObjectivesYao-Xiang Ding, Zhi-Hua Zhou. 7839-7848 [doi]
• Distributed k-Clustering for Data with Heavy NoiseShi Li, Xiangyu Guo. 7849-7857 [doi]
• Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte CarloHolden Lee, Andrej Risteski, Rong Ge 0001. 7858-7867 [doi]
• A General Method for Amortizing Variational FilteringJoseph Marino, Milan Cvitkovic, Yisong Yue. 7868-7879 [doi]
• A Reduction for Efficient LDA Topic ReconstructionMatteo Almanza, Flavio Chierichetti, Alessandro Panconesi, Andrea Vattani. 7880-7890 [doi]
• Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete DataDominik Linzner, Heinz Koeppl. 7891-7901 [doi]
• RenderNet: A deep convolutional network for differentiable rendering from 3D shapesThu Nguyen-Phuoc, Chuan Li, Stephen Balaban, Yong-Liang Yang. 7902-7912 [doi]
• Robust Hypothesis Testing Using Wasserstein Uncertainty SetsRui Gao, Liyan Xie, Yao Xie 0002, Huan Xu. 7913-7923 [doi]
• Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural NetworksZhihao Zheng, Pengyu Hong. 7924-7933 [doi]
• Monte-Carlo Tree Search for Constrained POMDPsJongmin Lee, Geon-hyeong Kim, Pascal Poupart, Kee-Eung Kim. 7934-7943 [doi]
• Learning to Repair Software Vulnerabilities with Generative Adversarial NetworksJacob Harer, Onur Ozdemir, Tomo Lazovich, Christopher P. Reale, Rebecca L. Russell, Louis Y. Kim, Sang Peter Chin. 7944-7954 [doi]
• Layer-Wise Coordination between Encoder and Decoder for Neural Machine TranslationTianyu He, Xu Tan, Yingce Xia, Di He, Tao Qin, Zhibo Chen 0001, Tie-Yan Liu. 7955-7965 [doi]
• Dirichlet belief networks for topic structure learningHe Zhao, Lan Du, Wray L. Buntine, Mingyuan Zhou. 7966-7977 [doi]
• Stochastic Expectation Maximization with Variance ReductionJianfei Chen, Jun Zhu, Yee Whye Teh, Tong Zhang. 7978-7988 [doi]
• Submodular Maximization via Gradient Ascent: The Case of Deep Submodular FunctionsWenruo Bai, William Stafford Noble, Jeff A. Bilmes. 7989-7999 [doi]
• The challenge of realistic music generation: modelling raw audio at scaleSander Dieleman, Aäron Van Den Oord, Karen Simonyan. 8000-8010 [doi]
• Spectral Signatures in Backdoor AttacksBrandon Tran, Jerry Li 0001, Aleksander Madry. 8011-8021 [doi]
• Reward learning from human preferences and demonstrations in AtariBorja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, Dario Amodei. 8022-8034 [doi]
• Approximate Knowledge Compilation by Online Collapsed Importance SamplingTal Friedman, Guy Van den Broeck. 8035-8045 [doi]
• Neural Arithmetic Logic UnitsAndrew Trask, Felix Hill, Scott E. Reed, Jack W. Rae, Chris Dyer, Phil Blunsom. 8046-8055 [doi]
• Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net TrainingYoujie Li, Mingchao Yu, Songze Li, Salman Avestimehr, Nam Sung Kim, Alexander G. Schwing. 8056-8067 [doi]
• Improved Expressivity Through Dendritic Neural NetworksXundong Wu, Xiangwen Liu, Wei Li, Qing Wu. 8068-8079 [doi]
• Efficient Anomaly Detection via Matrix SketchingVatsal Sharan, Parikshit Gopalan, Udi Wieder. 8080-8091 [doi]
• Learning to Specialize with Knowledge Distillation for Visual Question AnsweringJonghwan Mun, Kimin Lee, Jinwoo Shin, Bohyung Han. 8092-8102 [doi]
• A Lyapunov-based Approach to Safe Reinforcement LearningYinlam Chow, Ofir Nachum, Edgar A. Duéñez-Guzmán, Mohammad Ghavamzadeh. 8103-8112 [doi]
• Credit Assignment For Collective Multiagent RL With Global RewardsDuc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau. 8113-8124 [doi]
• Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple PassesLoucas Pillaud-Vivien, Alessandro Rudi, Francis Bach. 8125-8135 [doi]
• Does mitigating ML's impact disparity require treatment disparity?Zachary C. Lipton, Julian McAuley, Alexandra Chouldechova. 8136-8146 [doi]
• Proximal Graphical Event ModelsDebarun Bhattacharjya, Dharmashankar Subramanian, Tian Gao. 8147-8156 [doi]
• Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor EnvironmentsMahdi Imani, Seyede Fatemeh Ghoreishi, Ulisses Braga-Neto. 8157-8167 [doi]
• Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured DataYuanzhi Li, Yingyu Liang. 8168-8177 [doi]
• Hamiltonian Variational Auto-EncoderAnthony L. Caterini, Arnaud Doucet, Dino Sejdinovic. 8178-8188 [doi]
• Modelling and unsupervised learning of symmetric deformable object categoriesJames Thewlis, Hakan Bilen, Andrea Vedaldi. 8189-8200 [doi]
• Graphical model inference: Sequential Monte Carlo meets deterministic approximationsFredrik Lindsten, Jouni Helske, Matti Vihola. 8201-8211 [doi]
• Statistical mechanics of low-rank tensor decompositionJonathan Kadmon, Surya Ganguli. 8212-8222 [doi]
• Variational Bayesian Monte CarloLuigi Acerbi. 8223-8233 [doi]
• Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value ExpansionJacob Buckman, Danijar Hafner, George Tucker, Eugene Brevdo, Honglak Lee. 8234-8244 [doi]
• Efficient Online Portfolio with Logarithmic RegretHaipeng Luo, Chen-Yu Wei, Kai Zheng. 8245-8255 [doi]
• Algorithms and Theory for Multiple-Source AdaptationJudy Hoffman, Mehryar Mohri, Ningshan Zhang. 8256-8266 [doi]
• Online Reciprocal Recommendation with Theoretical Performance GuaranteesClaudio Gentile, Nikos Parotsidis, Fabio Vitale. 8267-8277 [doi]
• The promises and pitfalls of Stochastic Gradient Langevin DynamicsNicolas Brosse, Alain Durmus, Eric Moulines. 8278-8288 [doi]
• How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability PerspectiveLei Wu, Chao Ma, Weinan E. 8289-8298 [doi]
• Differentiable MPC for End-to-end Planning and ControlBrandon Amos, Ivan Dario Jimenez Rodriguez, Jacob Sacks, Byron Boots, J. Zico Kolter. 8299-8310 [doi]
• Bilevel learning of the Group Lasso structureJordan Frécon, Saverio Salzo, Massimiliano Pontil. 8311-8321 [doi]
• Constructing Unrestricted Adversarial Examples with Generative ModelsYang Song, Rui Shu, Nate Kushman, Stefano Ermon. 8322-8333 [doi]
• Information-theoretic Limits for Community Detection in Network ModelsChuyang Ke, Jean Honorio. 8334-8343 [doi]
• Learning Conditioned Graph Structures for Interpretable Visual Question AnsweringWill Norcliffe-Brown, Stathis Vafeias, Sarah Parisot. 8344-8353 [doi]
• Distributionally Robust Graphical ModelsRizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian D. Ziebart. 8354-8365 [doi]
• Transfer Learning with Neural AutoMLCatherine Wong, Neil Houlsby, Yifeng Lu, Andrea Gesmundo. 8366-8375 [doi]
• Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration ComplexityConghui Tan, Tong Zhang, Shiqian Ma, Ji Liu. 8376-8385 [doi]
• On preserving non-discrimination when combining expert adviceAvrim Blum, Suriya Gunasekar, Thodoris Lykouris, Nati Srebro. 8386-8397 [doi]
• Learning to Play With Intrinsically-Motivated, Self-Aware AgentsNick Haber, Damian Mrowca, Stephanie Wang, Fei-Fei Li, Daniel L. Yamins. 8398-8409 [doi]
• Scaling provable adversarial defensesEric Wong, Frank Schmidt, Jan Hendrik Metzen, J. Zico Kolter. 8410-8419 [doi]
• Deep Network for the Integrated 3D Sensing of Multiple People in Natural ImagesAndrei Zanfir, Elisabeta Marinoiu, Mihai Zanfir, Alin-Ionut Popa, Cristian Sminchisescu. 8420-8429 [doi]
• Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed PayoffsHan Shao, Xiaotian Yu, Irwin King, Michael R. Lyu. 8430-8439 [doi]
• Data-dependent PAC-Bayes priors via differential privacyGintare Karolina Dziugaite, Daniel M. Roy 0001. 8440-8450 [doi]
• Deep Poisson gamma dynamical systemsDandan Guo, Bo Chen 0001, Hao Zhang, Mingyuan Zhou. 8451-8461 [doi]
• Dimensionality Reduction has Quantifiable Imperfections: Two Geometric BoundsKry Yik-Chau Lui, Gavin Weiguang Ding, Ruitong Huang, Robert J. McCann. 8462-8472 [doi]
• Teaching Inverse Reinforcement Learners via Features and DemonstrationsLuis Haug, Sebastian Tschiatschek, Adish Singla. 8473-8482 [doi]
• Wasserstein Distributionally Robust Kalman FilteringSoroosh Shafieezadeh-Abadeh, Viet Anh Nguyen, Daniel Kuhn, Peyman Mohajerin Esfahani. 8483-8492 [doi]
• Generalisation of structural knowledge in the hippocampal-entorhinal systemJames C. R. Whittington, Timothy H. Muller, Shirely Mark, Caswell Barry, Tim E. J. Behrens. 8493-8504 [doi]
• Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic OptimizationBlake E. Woodworth, Jialei Wang, Adam Smith, Brendan McMahan, Nati Srebro. 8505-8515 [doi]
• Adversarial Regularizers in Inverse ProblemsSebastian Lunz, Carola Schönlieb, Ozan Öktem. 8516-8525 [doi]
• Clustering Redemption-Beyond the Impossibility of Kleinberg's AxiomsVincent Cohen-Addad, Varun Kanade, Frederik Mallmann-Trenn. 8526-8535 [doi]
• Co-teaching: Robust training of deep neural networks with extremely noisy labelsBo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor W. Tsang, Masashi Sugiyama. 8536-8546 [doi]
• Variational Inverse Control with Events: A General Framework for Data-Driven Reward DefinitionJustin Fu, Avi Singh, Dibya Ghosh, Larry Yang, Sergey Levine. 8547-8556 [doi]
• A convex program for bilinear inversion of sparse vectorsAlireza Aghasi, Ali Ahmed, Paul Hand, Babhru Joshi. 8557-8567 [doi]
• Adversarial Multiple Source Domain AdaptationHan Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, João P. Costeira, Geoffrey J. Gordon. 8568-8579 [doi]
• Neural Tangent Kernel: Convergence and Generalization in Neural NetworksArthur Jacot, Clément Hongler, Franck Gabriel. 8580-8589 [doi]
• Contextual Stochastic Block ModelsYash Deshpande, Subhabrata Sen, Andrea Montanari, Elchanan Mossel. 8590-8602 [doi]
• A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural NetworksJeffrey Chan, Valerio Perrone, Jeffrey P. Spence, Paul A. Jenkins, Sara Mathieson, Yun S. Song. 8603-8614 [doi]
• Sequential Attend, Infer, Repeat: Generative Modelling of Moving ObjectsAdam R. Kosiorek, Hyunjik Kim, Yee Whye Teh, Ingmar Posner. 8615-8625 [doi]
• Randomized Prior Functions for Deep Reinforcement LearningIan Osband, John Aslanides, Albin Cassirer. 8626-8638 [doi]
• Compact Representation of Uncertainty in ClusteringCraig Greenberg, Nicholas Monath, Ari Kobren, Patrick Flaherty, Andrew McGregor, Andrew McCallum. 8639-8649 [doi]
• Learning without the Phase: Regularized PhaseMax Achieves Optimal Sample ComplexityFariborz Salehi, Ehsan Abbasi, Babak Hassibi. 8655-8666 [doi]
• Multilingual Anchoring: Interactive Topic Modeling and Alignment Across LanguagesMichelle Yuan, Benjamin Van Durme, Jordan L. Ying. 8667-8677 [doi]
• Estimators for Multivariate Information Measures in General Probability SpacesArman Rahimzamani, Himanshu Asnani, Pramod Viswanath, Sreeram Kannan. 8678-8689 [doi]
• DeepPINK: reproducible feature selection in deep neural networksYang Young Lu, YingYing Fan, Jinchi Lv, William Stafford Noble. 8690-8700 [doi]
• HOUDINI: Lifelong Learning as Program SynthesisLazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles A. Sutton, Swarat Chaudhuri. 8701-8712 [doi]
• Searching for Efficient Multi-Scale Architectures for Dense Image PredictionLiang-Chieh Chen, Maxwell D. Collins, Yukun Zhu, George Papandreou, Barret Zoph, Florian Schroff, Hartwig Adam, Jonathon Shlens. 8713-8724 [doi]
• Orthogonally Decoupled Variational Gaussian ProcessesHugh Salimbeni, Ching-An Cheng, Byron Boots, Marc Peter Deisenroth. 8725-8734 [doi]
• Dendritic cortical microcircuits approximate the backpropagation algorithmJoão Sacramento, Rui Ponte Costa, Yoshua Bengio, Walter Senn. 8735-8746 [doi]
• Learning Plannable Representations with Causal InfoGANThanard Kurutach, Aviv Tamar, Ge Yang, Stuart J. Russell, Pieter Abbeel. 8747-8758 [doi]
• Uniform Convergence of Gradients for Non-Convex Learning and OptimizationDylan J. Foster, Ayush Sekhari, Karthik Sridharan. 8759-8770 [doi]
• Automatic differentiation in ML: Where we are and where we should be goingBart van Merrienboer, Olivier Breuleux, Arnaud Bergeron, Pascal Lamblin. 8771-8781 [doi]
• A Bayesian Nonparametric View on Count-Min SketchDiana Cai, Michael Mitzenmacher, Ryan P. Adams. 8782-8791 [doi]
• Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy LabelsZhilu Zhang, Mert R. Sabuncu. 8792-8802 [doi]
• Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNsTimur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry P. Vetrov, Andrew G. Wilson. 8803-8812 [doi]
• Flexible neural representation for physics predictionDamian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Fei-Fei Li, Josh Tenenbaum, Daniel L. Yamins. 8813-8824 [doi]
• Legendre Decomposition for TensorsMahito Sugiyama, Hiroyuki Nakahara, Koji Tsuda. 8825-8835 [doi]
• Reinforcement Learning of Theorem ProvingCezary Kaliszyk, Josef Urban, Henryk Michalewski, Miroslav Olsák. 8836-8847 [doi]
• Data Amplification: A Unified and Competitive Approach to Property EstimationYi Hao, Alon Orlitsky, Ananda Theertha Suresh, Yihong Wu 0001. 8848-8857 [doi]
• Group Equivariant Capsule NetworksJan Eric Lenssen, Matthias Fey, Pascal Libuschewski. 8858-8867 [doi]
• Stein Variational Gradient Descent as Moment MatchingQiang Liu, Dilin Wang. 8868-8877 [doi]
• Differential Privacy for Growing DatabasesRachel Cummings, Sara Krehbiel, Kevin A. Lai, Uthaipon Tao Tantipongpipat. 8878-8887 [doi]
• Exploration in Structured Reinforcement LearningJungseul Ok, Alexandre Proutière, Damianos Tranos. 8888-8896 [doi]
• A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite MatricesRudrasis Chakraborty, Chun-Hao Yang, Xingjian Zhen, Monami Banerjee, Derek Archer, David E. Vaillancourt, Vikas Singh, Baba C. Vemuri. 8897-8908 [doi]
• Balanced Policy Evaluation and LearningNathan Kallus. 8909-8920 [doi]
• Distributed Multitask Reinforcement Learning with Quadratic ConvergenceRasul Tutunov, DongHo Kim, Haitham Bou-Ammar. 8921-8930 [doi]
• Improving Neural Program Synthesis with Inferred Execution TracesRichard Shin, Illia Polosukhin, Dawn Song. 8931-8940 [doi]
• Adaptive Path-Integral Autoencoders: Representation Learning and Planning for Dynamical SystemsJung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi. 8941-8952 [doi]
• Policy-Conditioned Uncertainty Sets for Robust Markov Decision ProcessesAndrea Tirinzoni, Marek Petrik, Xiangli Chen, Brian D. Ziebart. 8953-8963 [doi]
• GLoMo: Unsupervised Learning of Transferable Relational GraphsZhilin Yang, Junbo Jake Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Ruslan R. Salakhutdinov, Yann LeCun. 8964-8975 [doi]
• Online Learning of Quantum StatesScott Aaronson, Xinyi Chen, Elad Hazan, Satyen Kale, Ashwin Nayak. 8976-8986 [doi]
• Wavelet regression and additive models for irregularly spaced dataAsad Haris, Ali Shojaie, Noah Simon. 8987-8997 [doi]
• Inferring Latent Velocities from Weather Radar Data using Gaussian ProcessesRico Angell, Daniel R. Sheldon. 8998-9007 [doi]
• A Structured Prediction Approach for Label RankingAnna Korba, Alexandre Garcia, Florence d'Alché-Buc. 9008-9018 [doi]
• Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier FeaturesMojmir Mutny, Andreas Krause. 9019-9030 [doi]
• FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural NetworkAditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain 0002, Manik Varma. 9031-9042 [doi]
• Reversible Recurrent Neural NetworksMatthew Mackay, Paul Vicol, Jimmy Ba, Roger B. Grosse. 9043-9054 [doi]
• SING: Symbol-to-Instrument Neural GeneratorAlexandre Défossez, Neil Zeghidour, Nicolas Usunier, Léon Bottou, Francis Bach. 9055-9065 [doi]
• Learning Compressed Transforms with Low Displacement RankAnna T. Thomas, Albert Gu, Tri Dao, Atri Rudra, Christopher Ré. 9066-9078 [doi]
• Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and ThresholdsXiaohan Chen, Jialin Liu 0003, Zhangyang Wang, Wotao Yin. 9079-9089 [doi]
• Iterative Value-Aware Model LearningAmir Massoud Farahmand. 9090-9101 [doi]
• Invariant Representations without Adversarial TrainingDaniel Moyer, Shuyang Gao, Rob Brekelmans, Aram Galstyan, Greg Ver Steeg. 9102-9111 [doi]
• Robot Learning in Homes: Improving Generalization and Reducing Dataset BiasAbhinav Gupta, Adithyavairavan Murali, Dhiraj Gandhi, Lerrel Pinto. 9112-9122 [doi]
• Learning Safe Policies with Expert GuidanceJessie Huang, Fa Wu, Doina Precup, Yang Cai 0001. 9123-9132 [doi]
• Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count dataEhsan Hajiramezanali, Siamak Zamani Dadaneh, Alireza Karbalayghareh, Mingyuan Zhou, Xiaoning Qian. 9133-9142 [doi]
• Learning SMaLL PredictorsVikas K. Garg, Ofer Dekel, Lin Xiao. 9143-9153 [doi]
• Phase Retrieval Under a Generative PriorPaul Hand, Oscar Leong, Vladislav Voroninski. 9154-9164 [doi]
• Quadrature-based features for kernel approximationMarina Munkhoeva, Yermek Kapushev, Evgeny Burnaev, Ivan V. Oseledets. 9165-9174 [doi]
• Reducing Network AgnostophobiaAkshay Raj Dhamija, Manuel Günther, Terrance E. Boult. 9175-9186 [doi]
• A Stein variational Newton methodGianluca Detommaso, Tiangang Cui, Youssef M. Marzouk, Alessio Spantini, Robert Scheichl. 9187-9197 [doi]
• Watch Your Step: Learning Node Embeddings via Graph AttentionSami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou', Alexander A. Alemi. 9198-9208 [doi]
• Visual Reinforcement Learning with Imagined GoalsAshvin Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine. 9209-9220 [doi]
• Deep Predictive Coding Network with Local Recurrent Processing for Object RecognitionKuan Han, Haiguang Wen, Yizhen Zhang, Di Fu, Eugenio Culurciello, Zhongming Liu. 9221-9233 [doi]
• PAC-Bayes bounds for stable algorithms with instance-dependent priorsOmar Rivasplata, Csaba Szepesvári, John Shawe-Taylor, Emilio Parrado-Hernández, Shiliang Sun. 9234-9244 [doi]
• Beyond Grids: Learning Graph Representations for Visual RecognitionYin Li, Abhinav Gupta. 9245-9255 [doi]
• The Limit Points of (Optimistic) Gradient Descent in Min-Max OptimizationConstantinos Daskalakis, Ioannis Panageas. 9256-9266 [doi]
• Coordinate Descent with Bandit SamplingFarnood Salehi, Patrick Thiran, L. Elisa Celis. 9267-9277 [doi]
• Deep Dynamical Modeling and Control of Unsteady Fluid FlowsJeremy Morton, Antony Jameson, Mykel J. Kochenderfer, Freddie D. Witherden. 9278-9288 [doi]
• Confounding-Robust Policy ImprovementNathan Kallus, Angela Zhou. 9289-9299 [doi]
• The Importance of Sampling inMeta-Reinforcement LearningBradly C. Stadie, Ge Yang, Rein Houthooft, Peter Chen, Yan Duan, Yuhuai Wu, Pieter Abbeel, Ilya Sutskever. 9300-9310 [doi]
• Representer Point Selection for Explaining Deep Neural NetworksChih-Kuan Yeh, Joon Sik Kim, Ian En-Hsu Yen, Pradeep Ravikumar. 9311-9321 [doi]
• The Effect of Network Width on the Performance of Large-batch TrainingLingjiao Chen, Hongyi Wang, Jinman Zhao, Dimitris S. Papailiopoulos, Paraschos Koutris. 9322-9332 [doi]
• SNIPER: Efficient Multi-Scale TrainingBharat Singh, Mahyar Najibi, Larry S. Davis. 9333-9343 [doi]
• The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture ModelsChen Dan, Liu Leqi, Bryon Aragam, Pradeep Ravikumar, Eric P. Xing. 9344-9354 [doi]
• Hardware Conditioned Policies for Multi-Robot Transfer LearningTao Chen, Adithyavairavan Murali, Abhinav Gupta. 9355-9366 [doi]
• Co-regularized Alignment for Unsupervised Domain AdaptationAbhishek Kumar, Prasanna Sattigeri, Kahini Wadhawan, Leonid Karlinsky, Rogério Schmidt Feris, Bill Freeman, Gregory W. Wornell. 9367-9378 [doi]
• Statistical and Computational Trade-Offs in Kernel K-MeansDaniele Calandriello, Lorenzo Rosasco. 9379-9389 [doi]
• Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and ArchitecturesSergey Bartunov, Adam Santoro, Blake A. Richards, Luke Marris, Geoffrey E. Hinton, Timothy P. Lillicrap. 9390-9400 [doi]
• Learning Attractor Dynamics for Generative MemoryYan Wu, Gregory Wayne, Karol Gregor, Timothy P. Lillicrap. 9401-9410 [doi]
• The emergence of multiple retinal cell types through efficient coding of natural moviesSamuel Ocko, Jack Lindsey, Surya Ganguli, Stéphane Deny. 9411-9422 [doi]
• Gather-Excite: Exploiting Feature Context in Convolutional Neural NetworksJie Hu, Li Shen, Samuel Albanie, Gang Sun, Andrea Vedaldi. 9423-9433 [doi]
• The Global Anchor Method for Quantifying Linguistic Shifts and Domain AdaptationZi Yin, Vin Sachidananda, Balaji Prabhakar. 9434-9445 [doi]
• Identification and Estimation of Causal Effects from Dependent DataEli Sherman, Ilya Shpitser. 9446-9457 [doi]
• Deepcode: Feedback Codes via Deep LearningHyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath. 9458-9468 [doi]
• Learning and Testing Causal Models with InterventionsJayadev Acharya, Arnab Bhattacharyya, Constantinos Daskalakis, Saravanan Kandasamy. 9469-9481 [doi]
• Implicit Bias of Gradient Descent on Linear Convolutional NetworksSuriya Gunasekar, Jason D. Lee, Daniel Soudry, Nati Srebro. 9482-9491 [doi]
• DAGs with NO TEARS: Continuous Optimization for Structure LearningXun Zheng, Bryon Aragam, Pradeep Ravikumar, Eric P. Xing. 9492-9503 [doi]
• PAC-Bayes Tree: weighted subtrees with guaranteesTin D. Nguyen, Samory Kpotufe. 9504-9512 [doi]
• Multi-objective Maximization of Monotone Submodular Functions with Cardinality ConstraintRajan Udwani. 9513-9524 [doi]
• Sanity Checks for Saliency MapsJulius Adebayo, Justin Gilmer, Michael Muelly, Ian J. Goodfellow, Moritz Hardt, Been Kim. 9525-9536 [doi]
• Probabilistic Model-Agnostic Meta-LearningChelsea Finn, Kelvin Xu, Sergey Levine. 9537-9548 [doi]
• Reinforcement Learning with Multiple Experts: A Bayesian Model Combination ApproachMichael Gimelfarb, Scott Sanner, Chi-Guhn Lee. 9549-9559 [doi]
• e-SNLI: Natural Language Inference with Natural Language ExplanationsOana-Maria Camburu, Tim Rocktäschel, Thomas Lukasiewicz, Phil Blunsom. 9560-9572 [doi]
• Fast Approximate Natural Gradient Descent in a Kronecker Factored EigenbasisThomas George, César Laurent, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent. 9573-9583 [doi]
• Learning convex bounds for linear quadratic control policy synthesisJack Umenberger, Thomas B. Schön. 9584-9595 [doi]
• Neural Proximal Gradient Descent for Compressive ImagingMorteza Mardani, Qingyun Sun, David L. Donoho, Vardan Papyan, Hatef Monajemi, Shreyas Vasanawala, John M. Pauly. 9596-9606 [doi]
• Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same RepresentationLiwei Wang, Lunjia Hu, Jiayuan Gu, Zhiqiang Hu, Yue Wu, Kun He 0001, John E. Hopcroft. 9607-9616 [doi]
• Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular MaximizationRad Niazadeh, Tim Roughgarden, Joshua R. Wang. 9617-9627 [doi]
• An intriguing failing of convolutional neural networks and the CoordConv solutionRosanne Liu, Joel Lehman, Piero Molino, Felipe Petroski Such, Eric Frank, Alex Sergeev, Jason Yosinski. 9628-9639 [doi]
• Trading robust representations for sample complexity through self-supervised visual experienceAndrea Tacchetti, Stephen Voinea, Georgios Evangelopoulos. 9640-9650 [doi]
• Invertibility of Convolutional Generative Networks from Partial MeasurementsFangchang Ma, Ulas Ayaz, Sertac Karaman. 9651-9660 [doi]
• Ex ante coordination and collusion in zero-sum multi-player extensive-form gamesGabriele Farina, Andrea Celli, Nicola Gatti 0001, Tuomas Sandholm. 9661-9671 [doi]
• Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual OptimizationHoi-To Wai, Zhuoran Yang, Zhaoran Wang, Mingyi Hong. 9672-9683 [doi]
• Improving Online Algorithms via ML PredictionsManish Purohit, Zoya Svitkina, Ravi Kumar. 9684-9693 [doi]
• Global Non-convex Optimization with Discretized DiffusionsMurat A. Erdogdu, Lester Mackey, Ohad Shamir. 9694-9703 [doi]
• Theoretical guarantees for EM under misspecified Gaussian mixture modelsRaaz Dwivedi, Nhat Ho, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan. 9704-9712 [doi]
• Coupled Variational Bayes via Optimization EmbeddingBo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song. 9713-9723 [doi]
• Improving Explorability in Variational Inference with Annealed Variational ObjectivesChin-Wei Huang, Shawn Tan, Alexandre Lacoste, Aaron C. Courville. 9724-9734 [doi]
• Latent Alignment and Variational AttentionYuntian Deng, Yoon Kim, Justin Chiu, Demi Guo, Alexander M. Rush. 9735-9747 [doi]
• Towards Deep Conversational RecommendationsRaymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, Chris Pal. 9748-9758 [doi]
• Unsupervised Depth Estimation, 3D Face Rotation and ReplacementJoel Ruben Antony Moniz, Christopher Beckham, Simon Rajotte, Sina Honari, Chris Pal. 9759-9769 [doi]
• Generalization Bounds for Uniformly Stable AlgorithmsVitaly Feldman, Jan Vondrák. 9770-9780 [doi]
• Deep Anomaly Detection Using Geometric TransformationsIzhak Golan, Ran El-Yaniv. 9781-9791 [doi]
• Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal TransportThéo Lacombe, Marco Cuturi, Steve Oudot. 9792-9802 [doi]
• Entropy Rate Estimation for Markov Chains with Large State SpaceYanjun Han, Jiantao Jiao, Chuan-Zheng Lee, Tsachy Weissman, Yihong Wu 0001, Tiancheng Yu. 9803-9814 [doi]
• Adaptive Methods for Nonconvex OptimizationManzil Zaheer, Sashank J. Reddi, Devendra Singh Sachan, Satyen Kale, Sanjiv Kumar. 9815-9825 [doi]
• Object-Oriented Dynamics PredictorGuangxiang Zhu, Zhiao Huang, Chongjie Zhang. 9826-9837 [doi]
• Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical ModelsAlexander Neitz, Giambattista Parascandolo, Stefan Bauer, Bernhard Schölkopf. 9838-9848 [doi]
• Scalable End-to-End Autonomous Vehicle Testing via Rare-event SimulationMatthew O'Kelly, Aman Sinha, Hongseok Namkoong, Russ Tedrake, John C. Duchi. 9849-9860 [doi]
• Reinforcement Learning for Solving the Vehicle Routing ProblemMohammadReza Nazari, Afshin Oroojlooy, Lawrence V. Snyder, Martin Takác. 9861-9871 [doi]
• ATOMO: Communication-efficient Learning via Atomic SparsificationHongyi Wang, Scott Sievert, Shengchao Liu, Zachary B. Charles, Dimitris S. Papailiopoulos, Stephen Wright. 9872-9883 [doi]
• Dynamic Network Model from Partial ObservationsElahe Ghalebi, Baharan Mirzasoleiman, Radu Grosu, Jure Leskovec. 9884-9894 [doi]
• Life-Long Disentangled Representation Learning with Cross-Domain Latent HomologiesAlessandro Achille, Tom Eccles, Loïc Matthey, Christopher Burgess, Nicholas Watters, Alexander Lerchner, Irina Higgins. 9895-9905 [doi]
• Maximizing acquisition functions for Bayesian optimizationJames T. Wilson, Frank Hutter, Marc Peter Deisenroth. 9906-9917 [doi]
• On Markov Chain Gradient DescentTao Sun, Yuejiao Sun, Wotao Yin. 9918-9927 [doi]
• Variance-Reduced Stochastic Gradient Descent on Streaming DataEllango Jothimurugesan, Ashraf Tahmasbi, Phillip B. Gibbons, Srikanta Tirthapura. 9928-9937 [doi]
• Online Robust Policy Learning in the Presence of Unknown AdversariesAaron J. Havens, Zhanhong Jiang, Soumik Sarkar. 9938-9948 [doi]
• Uplift Modeling from Separate LabelsIkko Yamane, Florian Yger, Jamal Atif, Masashi Sugiyama. 9949-9959 [doi]
• Learning Invariances using the Marginal LikelihoodMark van der Wilk, Matthias Bauer, S. T. John, James Hensman. 9960-9970 [doi]
• Non-delusional Q-learning and value-iterationTyler Lu, Dale Schuurmans, Craig Boutilier. 9971-9981 [doi]
• Using Large Ensembles of Control Variates for Variational InferenceTomas Geffner, Justin Domke. 9982-9992 [doi]
• Post: Device Placement with Cross-Entropy Minimization and Proximal Policy OptimizationYuanxiang Gao, Li Chen 0019, Baochun Li. 9993-10002 [doi]
• Learning to Reason with Third Order Tensor ProductsImanol Schlag, Jürgen Schmidhuber. 10003-10014 [doi]
• Memory Augmented Policy Optimization for Program Synthesis and Semantic ParsingChen Liang, Mohammad Norouzi 0002, Jonathan Berant, Quoc V. Le, Ni Lao. 10015-10027 [doi]
• Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence DiagramsTam Le, Makoto Yamada. 10028-10039 [doi]
• Neural Voice Cloning with a Few SamplesSercan Ömer Arik, Jitong Chen, Kainan Peng, Wei Ping, Yanqi Zhou. 10040-10050 [doi]
• Blind Deconvolutional Phase Retrieval via Convex ProgrammingAli Ahmed, Alireza Aghasi, Paul Hand. 10051-10061 [doi]
• Scalable Laplacian K-modesImtiaz Masud Ziko, Eric Granger, Ismail Ben Ayed. 10062-10072 [doi]
• A Retrieve-and-Edit Framework for Predicting Structured OutputsTatsunori B. Hashimoto, Kelvin Guu, Yonatan Oren, Percy S. Liang. 10073-10083 [doi]
• Testing for Families of Distributions via the Fourier TransformAlistair Stewart, Ilias Diakonikolas, Clément L. Canonne. 10084-10095 [doi]
• Thwarting Adversarial Examples: An L_0-Robust Sparse Fourier TransformMitali Bafna, Jack Murtagh, Nikhil Vyas. 10096-10106 [doi]
• Blockwise Parallel Decoding for Deep Autoregressive ModelsMitchell Stern, Noam Shazeer, Jakob Uszkoreit. 10107-10116 [doi]
• Low-Rank Tucker Decomposition of Large Tensors Using TensorSketchOsman Asif Malik, Stephen Becker. 10117-10127 [doi]
• A Simple Cache Model for Image RecognitionEmin Orhan. 10128-10137 [doi]
• Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural NetworkRisi Kondor, Zhen Lin, Shubhendu Trivedi. 10138-10147 [doi]
• Bayesian Nonparametric Spectral EstimationFelipe Tobar. 10148-10158 [doi]
• A Spectral View of Adversarially Robust FeaturesShivam Garg, Vatsal Sharan, Brian Hu Zhang, Gregory Valiant. 10159-10169 [doi]
• Synaptic Strength For Convolutional Neural NetworkChen Lin, Zhao Zhong, Wu Wei, Junjie Yan. 10170-10179 [doi]
• Human-in-the-Loop Interpretability PriorIsaac Lage, Andrew Slavin Ross, Samuel J. Gershman, Been Kim, Finale Doshi-Velez. 10180-10189 [doi]
• Learning To Learn Around A Common MeanGiulia Denevi, Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil. 10190-10200 [doi]
• Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable ProgrammingFei Wang, James M. Decker, Xilun Wu, Grégory M. Essertel, Tiark Rompf. 10201-10212 [doi]
• Learning with SGD and Random FeaturesLuigi Carratino, Alessandro Rudi, Lorenzo Rosasco. 10213-10224 [doi]
• Total stochastic gradient algorithms and applications in reinforcement learningPaavo Parmas. 10225-10235 [doi]
• Glow: Generative Flow with Invertible 1x1 ConvolutionsDiederik P. Kingma, Prafulla Dhariwal. 10236-10245 [doi]
• Nonparametric Density Estimation under Adversarial LossesShashank Singh 0005, Ananya Uppal, Boyue Li, Chun-Liang Li, Manzil Zaheer, Barnabás Póczos. 10246-10257 [doi]
• Generalizing Point Embeddings using the Wasserstein Space of Elliptical DistributionsBoris Muzellec, Marco Cuturi. 10258-10269 [doi]
• Learning to Share and Hide Intentions using Information RegularizationDaniel Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matthew Botvinick, David J. Schwab. 10270-10281 [doi]
• Predictive Approximate Bayesian Computation via Saddle PointsYingxiang Yang, Bo Dai, Negar Kiyavash, Niao He. 10282-10291 [doi]
• Robustness of conditional GANs to noisy labelsKiran Koshy Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh. 10292-10303 [doi]
• Robust Learning of Fixed-Structure Bayesian NetworksYu Cheng 0002, Ilias Diakonikolas, Daniel Kane, Alistair Stewart. 10304-10316 [doi]
• Improving Simple Models with Confidence ProfilesAmit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss, Peder A. Olsen. 10317-10327 [doi]
• PCA of high dimensional random walks with comparison to neural network trainingJoseph M. Antognini, Jascha Sohl-Dickstein. 10328-10337 [doi]
• Learning to Solve SMT FormulasMislav Balunovic, Pavol Bielik, Martin T. Vechev. 10338-10349 [doi]
• Lifted Weighted Mini-BucketNicholas Gallo, Alexander T. Ihler. 10350-10358 [doi]
• Learning and Inference in Hilbert Space with Quantum Graphical ModelsSiddarth Srinivasan, Carlton Downey, Byron Boots. 10359-10368 [doi]
• Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information BoundHadi Kazemi, Sobhan Soleymani, Fariborz Taherkhani, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi. 10369-10379 [doi]
• Adversarial Risk and Robustness: General Definitions and Implications for the Uniform DistributionDimitrios I. Diochnos, Saeed Mahloujifar, Mohammad Mahmoody. 10380-10389 [doi]
• Gaussian Process Prior Variational AutoencodersFrancesco Paolo Casale, Adrian V. Dalca, Luca Saglietti, Jennifer Listgarten, Nicoló Fusi. 10390-10401 [doi]
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric DataMaurice Weiler, Mario Geiger, Max Welling, Wouter Boomsma, Taco Cohen. 10402-10413 [doi]
• Context-aware Synthesis and Placement of Object InstancesDonghoon Lee, Sifei Liu, Jinwei Gu, Ming-Yu Liu 0001, Ming-Hsuan Yang 0001, Jan Kautz. 10414-10424 [doi]
• Convex Elicitation of Continuous PropertiesJessica Finocchiaro, Rafael M. Frongillo. 10425-10434 [doi]
• Mesh-TensorFlow: Deep Learning for SupercomputersNoam Shazeer, Youlong Cheng, Niki Parmar, Dustin Tran, Ashish Vaswani, Penporn Koanantakool, Peter Hawkins, HyoukJoong Lee, Mingsheng Hong, Cliff Young, Ryan Sepassi, Blake A. Hechtman. 10435-10444 [doi]
• Learning Abstract OptionsMatthew Riemer, Miao Liu, Gerald Tesauro. 10445-10455 [doi]
• Bounded-Loss Private Prediction MarketsRafael M. Frongillo, Bo Waggoner. 10456-10465 [doi]
• Temporal alignment and latent Gaussian process factor inference in population spike trainsLea Duncker, Maneesh Sahani. 10466-10476 [doi]
• Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe NoiseDan Hendrycks, Mantas Mazeika, Duncan Wilson, Kevin Gimpel. 10477-10486 [doi]
• Discretely Relaxing Continuous Variables for tractable Variational InferenceTrefor Evans, Prasanth Nair. 10487-10497 [doi]
• Regret bounds for meta Bayesian optimization with an unknown Gaussian process priorZi Wang, Beomjoon Kim, Leslie Pack Kaelbling. 10498-10509 [doi]
• Diversity-Driven Exploration Strategy for Deep Reinforcement LearningZhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Tsu-Jui Fu, Chun-Yi Lee. 10510-10521 [doi]
• Deep Generative Models with Learnable Knowledge ConstraintsZhiting Hu, Zichao Yang, Ruslan R. Salakhutdinov, Lianhui Qin, Xiaodan Liang, Haoye Dong, Eric P. Xing. 10522-10533 [doi]
• The Sparse Manifold TransformYubei Chen, Dylan M. Paiton, Bruno A. Olshausen. 10534-10545 [doi]
• Bayesian Structure Learning by Recursive BootstrapRaanan Y. Yehezkel Rohekar, Yaniv Gurwicz, Shami Nisimov, Guy Koren, Gal Novik. 10546-10556 [doi]
• Complex Gated Recurrent Neural NetworksMoritz Wolter, Angela Yao. 10557-10567 [doi]
• Learning a Warping Distance from Unlabeled Time Series Using Sequence AutoencodersAbubakar Abid, James Y. Zou. 10568-10578 [doi]
• Streamlining Variational Inference for Constraint Satisfaction ProblemsAditya Grover, Tudor Achim, Stefano Ermon. 10579-10589 [doi]
• Fast deep reinforcement learning using online adjustments from the pastSteven Hansen, Alexander Pritzel, Pablo Sprechmann, André Barreto, Charles Blundell. 10590-10600 [doi]
• Improved Network Robustness with Adversary CriticAlexander Matyasko, Lap-Pui Chau. 10601-10610 [doi]
• Regret Bounds for Online Portfolio Selection with a Cardinality ConstraintShinji Ito, Daisuke Hatano, Hanna Sumita, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi. 10611-10620 [doi]
• Sketching Method for Large Scale Combinatorial InferenceWei Sun, Junwei Lu, Han Liu 0001. 10621-10630 [doi]
• Connecting Optimization and Regularization PathsArun Sai Suggala, Adarsh Prasad, Pradeep Ravikumar. 10631-10641 [doi]
• Fully Neural Network Based Speech Recognition on Mobile and Embedded DevicesJinhwan Park, Yoonho Boo, Iksoo Choi, Sungho Shin, Wonyong Sung. 10642-10653 [doi]
• Understanding Regularized Spectral Clustering via Graph ConductanceYilin Zhang, Karl Rohe. 10654-10663 [doi]
• Data-Driven Clustering via Parameterized Lloyd's FamiliesMaria-Florina Balcan, Travis Dick, Colin White. 10664-10674 [doi]
• Learning Beam Search Policies via Imitation LearningRenato Negrinho, Matthew R. Gormley, Geoffrey J. Gordon. 10675-10684 [doi]
• Benefits of over-parameterization with EMJi Xu, Daniel J. Hsu, Arian Maleki. 10685-10695 [doi]
• Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learningRui Luo, Jianhong Wang, Yaodong Yang, Jun Wang 0012, Zhanxing Zhu. 10696-10705 [doi]
• Robust Subspace Approximation in a StreamRoie Levin, Anish Prasad Sevekari, David P. Woodruff. 10706-10716 [doi]
• Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence IssuesSoumendu Sundar Mukherjee, Purnamrita Sarkar, Y. X. Rachel Wang, Bowei Yan. 10717-10727 [doi]
• Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic ProblemsYair Carmon, John C. Duchi. 10728-10738 [doi]
• Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific LanguageMatthew D. Hoffman. 10739-10749 [doi]
• DropBlock: A regularization method for convolutional networksGolnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le. 10750-10760 [doi]
• Forward Modeling for Partial Observation Strategy Games - A StarCraft DefoggerGabriel Synnaeve, Zeming Lin, Jonas Gehring, Daniel Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier. 10761-10771 [doi]
• With Friends Like These, Who Needs Adversaries?Saumya Jetley, Nicholas A. Lord, Philip H. S. Torr. 10772-10782 [doi]
• Decentralize and Randomize: Faster Algorithm for Wasserstein BarycentersPavel Dvurechenskii, Darina Dvinskikh, Alexander Gasnikov, César A. Uribe, Angelia Nedich. 10783-10793 [doi]
• Joint Autoregressive and Hierarchical Priors for Learned Image CompressionDavid Minnen, Johannes Ballé, George Toderici. 10794-10803 [doi]
• Learning Temporal Point Processes via Reinforcement LearningShuang Li 0002, Shuai Xiao, Shixiang Zhu, Nan Du, Yao Xie 0002, Le Song. 10804-10814 [doi]
• Bias and Generalization in Deep Generative Models: An Empirical StudyShengjia Zhao, Hongyu Ren, Arianna Yuan, Jiaming Song, Noah Goodman, Stefano Ermon. 10815-10824 [doi]
• Fast and Effective Robustness CertificationGagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin T. Vechev. 10825-10836 [doi]
• Support Recovery for Orthogonal Matching Pursuit: Upper and Lower boundsRaghav Somani, Chirag Gupta, Prateek Jain 0002, Praneeth Netrapalli. 10837-10847 [doi]
• Differentially Private Change-Point DetectionRachel Cummings, Sara Krehbiel, Yajun Mei, Rui Tuo, Wanrong Zhang. 10848-10857 [doi]
• Multi-value Rule Sets for Interpretable Classification with Feature-Efficient RepresentationsTong Wang. 10858-10868 [doi]
• Domain Adaptation by Using Causal Inference to Predict Invariant Conditional DistributionsSara Magliacane, Thijs van Ommen, Tom Claassen, Stephan Bongers, Philip Versteeg, Joris M. Mooij. 10869-10879 [doi]
• Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of NeuronsNima Anari, Constantinos Daskalakis, Wolfgang Maass 0001, Christos H. Papadimitriou, Amin Saberi, Santosh Vempala. 10880-10890 [doi]
• MixLasso: Generalized Mixed Regression via Convex Atomic-Norm RegularizationIan En-Hsu Yen, Wei-Cheng Lee, Kai Zhong, Sung-En Chang, Pradeep Ravikumar, Shou-de Lin. 10891-10899 [doi]
• Semidefinite relaxations for certifying robustness to adversarial examplesAditi Raghunathan, Jacob Steinhardt, Percy S. Liang. 10900-10910 [doi]
• Removing Hidden Confounding by Experimental GroundingNathan Kallus, Aahlad Manas Puli, Uri Shalit. 10911-10920 [doi]
• Topkapi: Parallel and Fast Sketches for Finding Top-K Frequent ElementsAnkush Mandal, He Jiang, Anshumali Shrivastava, Vivek Sarkar. 10921-10931 [doi]
• Contrastive Learning from Pairwise MeasurementsYi Chen, Zhuoran Yang, Yuchen Xie, Zhaoran Wang. 10932-10941 [doi]
• Point process latent variable models of larval zebrafish behaviorAnuj Sharma, Robert Johnson, Florian Engert, Scott W. Linderman. 10942-10953 [doi]
• Computationally and statistically efficient learning of causal Bayes nets using path queriesKevin Bello, Jean Honorio. 10954-10964 [doi]
• Sparse PCA from Sparse Linear RegressionGuy Bresler, Sung Min Park, Madalina Persu. 10965-10975 [doi]
• Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained DevicesDon Dennis, Chirag Pabbaraju, Harsha Vardhan Simhadri, Prateek Jain 0002. 10976-10987 [doi]
• Transfer of Deep Reactive Policies for MDP PlanningAniket (Nick) Bajpai, Sankalp Garg, None. 10988-10998 [doi]
• The Price of Fair PCA: One Extra dimensionSamira Samadi, Uthaipon Tao Tantipongpipat, Jamie H. Morgenstern, Mohit Singh, Santosh Vempala. 10999-11010 [doi]
• GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model ShrinkingPatrick H. Chen, Si Si, Yang Li, Ciprian Chelba, Cho-Jui Hsieh. 11011-11021 [doi]