Table of Contents

• Semi-supervised learning, causality, and the conditional cluster assumptionJulius von Kügelgen, Alexander Mey, Marco Loog, Bernhard Schölkopf. 11 [doi]
• Finite-sample Analysis of Greedy-GQ with Linear Function Approximation under Markovian NoiseYue Wang, Shaofeng Zou. 17 [doi]
• PAC-Bayesian Contrastive Unsupervised Representation LearningKento Nozawa, Pascal Germain, Benjamin Guedj. 24 [doi]
• Static and Dynamic Values of Computation in MCTSEren Sezener, Peter Dayan. 26 [doi]
• Kernel Conditional Moment Test via Maximum Moment RestrictionKrikamol Muandet, Wittawat Jitkrittum, Jonas M. Kübler. 29 [doi]
• Bounding the expected run-time of nonconvex optimization with early stoppingThomas Flynn, Kwangmin Yu, Abid Malik, Nicholas D'Imperio, Shinjae Yoo. 32 [doi]
• Amortized variance reduction for doubly stochastic objectiveAyman Boustati, Sattar Vakili, James Hensman, S. T. John. 39 [doi]
• Randomized Exploration for Non-Stationary Stochastic Linear BanditsBaekjin Kim, Ambuj Tewari. 49 [doi]
• Divergence-Based Motivation for Online EM and Combining Hidden Variable ModelsEhsan Amid, Manfred K. Warmuth. 54 [doi]
• Iterative Channel Estimation for Discrete Denoising under Channel UncertaintyHongjoon Ahn, Taesup Moon. 55 [doi]
• Nonparametric Fisher Geometry with Application to Density EstimationAndrew Holbrook, Shiwei Lan, Jeffrey Streets, Babak Shahbaba. 58 [doi]
• Learning Intrinsic Rewards as a Bi-Level Optimization ProblemBradly Stadie, Lunjun Zhang, Jimmy Ba. 66 [doi]
• Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical SystemsSeyed Mohammad Asghari, Yi Ouyang 0002, Ashutosh Nayyar. 71 [doi]
• Learning Behaviors with Uncertain Human FeedbackXu He, Haipeng Chen 0001, Bo An 0001. 73 [doi]
• Regret Analysis of Bandit Problems with Causal Background KnowledgeYangyi Lu, Amirhossein Meisami, Ambuj Tewari, William Yan. 77 [doi]
• Evaluation of Causal Structure Learning Algorithms via Risk EstimationMarco Eigenmann, Sach Mukherjee, Marloes H. Maathuis. 93 [doi]
• Kidney Exchange with Inhomogeneous Edge Existence UncertaintyHoda Bidkhori, John Dickerson 0001, Duncan C. McElfresh, Ke Ren. 94 [doi]
• On the design of consequential ranking algorithmsBehzad Tabibian, Vicenç Gómez, Abir De, Bernhard Schölkopf, Manuel Gomez-Rodriguez. 95 [doi]
• Fair Contextual Multi-Armed Bandits: Theory and ExperimentsYifang Chen, Alex Cuellar, Haipeng Luo, Jignesh Modi, Heramb Nemlekar, Stefanos Nikolaidis. 99 [doi]
• Submodular Bandit Problem Under Multiple ConstraintsSho Takemori, Masahiro Sato, Takashi Sonoda, Janmajay Singh, Tomoko Ohkuma. 104 [doi]
• Exploration Analysis in Finite-Horizon Turn-based Stochastic GamesJialian Li, Yichi Zhou, Tongzheng Ren, Jun Zhu 0001. 105 [doi]
• Amortized Nesterov's Momentum: A Robust Momentum and Its Application to Deep LearningKaiwen Zhou, Yanghua Jin, Qinghua Ding, James Cheng. 108 [doi]
• Testing Goodness of Fit of Conditional Density Models with KernelsWittawat Jitkrittum, Heishiro Kanagawa, Bernhard Schölkopf. 109 [doi]
• Scalable and Flexible Clustering of Grouped Data via Parallel and Distributed Sampling in Versatile Hierarchical Dirichlet ProcessesOr Dinari, Oren Freifeld. 115 [doi]
• Statistically Efficient Greedy Equivalence SearchMax Chickering. 117 [doi]
• Robust Collective Classification against Structural AttacksKai Zhou, Yevgeniy Vorobeychik. 119 [doi]
• Efficient Rollout Strategies for Bayesian OptimizationEric Hans Lee, David Eriksson, David Bindel, Bolong Cheng, Mike Mccourt. 124 [doi]
• IDA with Background KnowledgeZhuangyan Fang, Yangbo He. 127 [doi]
• p-norm MaximizationYifei Shen, Ye Xue, Jun Zhang 0004, Khaled B. Letaief, Vincent Lau 0001. 128 [doi]
• Collapsible IDA: Collapsing Parental Sets for Locally Estimating Possible Causal EffectsYue Liu, Zhuangyan Fang, Yangbo He, Zhi Geng. 129 [doi]
• Learning Joint Nonlinear Effects from Single-variable Interventions in the Presence of Hidden ConfoundersSorawit Saengkyongam, Ricardo Silva. 131 [doi]
• Causal screening in dynamical systemsSøren Wengel Mogensen. 132 [doi]
• Bayesian Online Prediction of Change PointsDiego Agudelo-España, Sebastián Gómez-González, Stefan Bauer, Bernhard Schölkopf, Jan Peters 0001. 137 [doi]
• Walking on Two Legs: Learning Image Segmentation with Noisy LabelsGuohua Cheng, Hongli Ji, Yan Tian. 140 [doi]
• Election Control by Manipulating Issue SignificanceAndrew Estornell, Sanmay Das, Edith Elkind, Yevgeniy Vorobeychik. 151 [doi]
• Coresets for Estimating Means and Mean Square Error with Limited Greedy SamplesSaeed Vahidian, Baharan Mirzasoleiman, Alexander Cloninger. 152 [doi]
• Robust Spatial-Temporal Incident PredictionAyan Mukhopadhyay, Kai Wang, Andrew Perrault, Mykel J. Kochenderfer, Milind Tambe, Yevgeniy Vorobeychik. 155 [doi]
• Lagrangian Decomposition for Neural Network VerificationRudy Bunel, Alessandro De Palma, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar. 159 [doi]
• Robust modal regression with direct gradient approximation of modal regression riskHiroaki Sasaki, Tomoya Sakai, Takafumi Kanamori. 173 [doi]
• A Simple Online Algorithm for Competing with Dynamic ComparatorsYu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou. 175 [doi]
• Skewness Ranking Optimization for Personalized RecommendationYu-Neng Chuang, Chih-Ming Chen 0003, Chuan-Ju Wang, Ming-Feng Tsai. 176 [doi]
• High Dimensional Discrete Integration over the HypergridRaj Kumar Maity, Arya Mazumdar, Soumyabrata Pal. 177 [doi]
• Neural Likelihoods via Cumulative Distribution FunctionsPawel M. Chilinski, Ricardo Silva. 180 [doi]
• Unknown mixing times in apprenticeship and reinforcement learningTom Zahavy, Alon Cohen, Haim Kaplan, Yishay Mansour. 193 [doi]
• TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLPNils Rethmeier, Vageesh Kumar Saxena, Isabelle Augenstein. 197 [doi]
• What You See May Not Be What You Get: UCB Bandit Algorithms Robust to ε-ContaminationLaura Niss, Ambuj Tewari. 198 [doi]
• The Hawkes Edge Partition Model for Continuous-time Event-based Temporal NetworksSikun Yang, Heinz Koeppl. 201 [doi]
• Learning by Repetition: Stochastic Multi-armed Bandits under Priming EffectPriyank Agrawal, Theja Tulabandhula. 202 [doi]
• Compositional uncertainty in deep Gaussian processesIvan Ustyuzhaninov, Ieva Kazlauskaite, Markus Kaiser, Erik Bodin, Neill D. F. Campbell, Carl Henrik Ek. 206 [doi]
• Streaming Nonlinear Bayesian Tensor DecompositionZhimeng Pan, Zheng Wang, Shandian Zhe. 210 [doi]
• Relaxed Multivariate Bernoulli Distribution and Its Applications to Deep Generative ModelsXi Wang, Junming Yin. 218 [doi]
• One-Bit Compressed Sensing via One-Shot Hard ThresholdingJie Shen. 221 [doi]
• GPIRT: A Gaussian Process Model for Item Response TheoryJBrandon Duck-Mayr, Roman Garnett, Jacob M. Montgomery. 227 [doi]
• Identifying causal effects in maximally oriented partially directed acyclic graphsEmilija Perkovic. 229 [doi]
• Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient EstimatorSiamak Zamani Dadaneh, Shahin Boluki, Mingzhang Yin, Mingyuan Zhou, Xiaoning Qian. 232 [doi]
• Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical ComparisonTengyang Xie, Nan Jiang. 235 [doi]
• Towards Threshold Invariant Fair ClassificationMingliang Chen, Min Wu 0001. 237 [doi]
• Optimal Statistical Hypothesis Testing for Social ChoiceLirong Xia. 238 [doi]
• A SUPER* Algorithm to Optimize Paper Bidding in Peer ReviewTanner Fiez, Nihar B. Shah, Lillian J. Ratliff. 240 [doi]
• Measurement Dependence Inducing Latent Causal ModelsAlex Markham, Moritz Grosse-Wentrup. 244 [doi]
• The Indian Chefs ProcessPatrick Dallaire, Luca Ambrogioni, Ludovic Trottier, Umut Güçlü, Max Hinne, Philippe Giguère, Marcel van Gerven, François Laviolette. 245 [doi]
• Spectral Methods for Ranking with Scarce DataLalit Jain, Anna C. Gilbert, Umang Varma. 249 [doi]
• Anchored Causal Inference in the Presence of Measurement ErrorBasil Saeed, Anastasiya Belyaeva, Yuhao Wang 0005, Caroline Uhler. 253 [doi]
• How Private Are Commonly-Used Voting Rules?Ao Liu, Yun Lu, Lirong Xia, Vassilis Zikas. 262 [doi]
• Differentially Private Small Dataset Release Using Random ProjectionsLovedeep Gondara, Ke Wang 0001. 264 [doi]
• Semi-supervised Sequential Generative ModelsMichael Teng, Tuan Anh Le, Adam Scibior, Frank Wood. 272 [doi]
• Robust contrastive learning and nonlinear ICA in the presence of outliersHiroaki Sasaki, Takashi Takenouchi, Ricardo Pio Monti, Aapo Hyvärinen. 273 [doi]
• Selling Data at an Auction under Privacy ConstraintsMengxiao Zhang, Fernando Beltrán, Jiamou Liu. 274 [doi]
• Mixed-Membership Stochastic Block Models for Weighted NetworksAdrien Dulac, Éric Gaussier, Christine Largeron. 276 [doi]
• MaskAAE: Latent space optimization for Adversarial Auto-EncodersArnab Kumar Mondal, Sankalan Pal Chowdhury, Aravind Jayendran, Himanshu Asnani, Parag Singla, Prathosh A. P.. 281 [doi]
• Slice Sampling for General Completely Random MeasuresPeiyuan Zhu, Alexandre Bouchard-Côté, Trevor Campbell. 282 [doi]
• Semi-Supervised Learning: the Case When Unlabeled Data is Equally UsefulJingge Zhu. 304 [doi]
• Generalized Bayesian Posterior Expectation Distillation for Deep Neural NetworksMeet P. Vadera, Brian Jalaian, Benjamin M. Marlin. 305 [doi]
• Complex Markov Logic Networks: Expressivity and LiftabilityOndrej Kuzelka. 310 [doi]
• Faster algorithms for Markov equivalenceZhongYi Hu, Robin Evans. 311 [doi]
• Verifying Individual Fairness in Machine Learning ModelsPhilips George John, Deepak Vijaykeerthy, Diptikalyan Saha. 327 [doi]
• An Interpretable and Sample Efficient Deep Kernel for Gaussian ProcessYijue Dai, Tianjian Zhang, Zhidi Lin, Feng Yin, Sergios Theodoridis, Shuguang Cui. 328 [doi]
• Amortized Bayesian Optimization over Discrete SpacesKevin Swersky, Yulia Rubanova, David Dohan, Kevin Murphy. 329 [doi]
• Batch simulations and uncertainty quantification in Gaussian process surrogate approximate Bayesian computationMarko Järvenpää, Aki Vehtari, Pekka Marttinen. 334 [doi]
• Deep Sigma Point ProcessesMartin Jankowiak, Geoff Pleiss, Jacob R. Gardner. 339 [doi]
• Robust k-means++Amit Deshpande, Praneeth Kacham, Rameshwar Pratap. 340 [doi]
• On Counterfactual Explanations under Predictive MultiplicityMartin Pawelczyk, Klaus Broelemann, Gjergji Kasneci. 350 [doi]
• A Practical Riemannian Algorithm for Computing Dominant Generalized EigenspaceZhiqiang Xu, Ping Li 0001. 354 [doi]
• No-regret Exploration in Contextual Reinforcement LearningAditya Modi 0002, Ambuj Tewari. 355 [doi]
• Layering-MCMC for Structure Learning in Bayesian NetworksJussi Viinikka, Mikko Koivisto. 356 [doi]
• C-MI-GAN : Estimation of Conditional Mutual Information using MinMax formulationArnab Kumar Mondal, Arnab Bhattacharjee, Sudipto Mukherjee, Himanshu Asnani, Sreeram Kannan, Prathosh A. P.. 358 [doi]
• Stochastic Variational Inference for Dynamic Correlated Topic ModelsFederico Tomasi, Praveen Chandar, Gal Levy-Fix, Mounia Lalmas-Roelleke, Zhenwen Dai. 365 [doi]
• Adversarial Learning for 3D MatchingWei Xing, Brian D. Ziebart. 366 [doi]
• Ordering Variables for Weighted Model IntegrationVincent Derkinderen, Evert Heylen, Pedro Zuidberg Dos Martires, Samuel Kolb, Luc De Raedt. 367 [doi]
• Online Parameter-Free Learning of Multiple Low Variance TasksGiulia Denevi, Massimiliano Pontil, Dimitrios Stamos. 368 [doi]
• Zeroth Order Non-convex optimization with Dueling-Choice BanditsYichong Xu, Aparna Joshi, Aarti Singh, Artur Dubrawski. 372 [doi]
• Semi-bandit Optimization in the Dispersed SettingTravis Dick, Wesley Pegden, Maria-Florina Balcan. 374 [doi]
• Adapting Text Embeddings for Causal InferenceVictor Veitch, Dhanya Sridhar, David M. Blei. 376 [doi]
• Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable ModelsZhijian Ou, Yunfu Song. 377 [doi]
• Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time SeriesHermanni Hälvä, Aapo Hyvärinen. 379 [doi]
• Identification and Estimation of Causal Effects Defined by Shift InterventionsNumair Sani, Jaron J. R. Lee, Ilya Shpitser. 388 [doi]
• Risk Bounds for Low Cost Bipartite RankingSan Gultekin, John W. Paisley. 389 [doi]
• Multitask Soft Option LearningMaximilian Igl, Andrew Gambardella, Jinke He, Nantas Nardelli, N. Siddharth 0001, Wendelin Boehmer, Shimon Whiteson. 397 [doi]
• 99% of Worker-Master Communication in Distributed Optimization Is Not NeededKonstantin Mishchenko, Filip Hanzely, Peter Richtárik. 404 [doi]
• Graphical continuous Lyapunov modelsGherardo Varando, Niels Richard Hansen. 407 [doi]
• Structure Learning for Cyclic Linear Causal ModelsCarlos Améndola, Philipp Dettling, Mathias Drton, Federica Onori, Jun Wu. 408 [doi]
• Sensor Placement for Spatial Gaussian Processes with Integral ObservationsKrista Longi, Chang Rajani, Tom Sillanpää, Joni Mäkinen, Timo Rauhala, Ari Salmi, Edward Hæggström, Arto Klami. 411 [doi]
• Active Model Estimation in Markov Decision ProcessesJean Tarbouriech, Shubhanshu Shekhar, Matteo Pirotta, Mohammad Ghavamzadeh, Alessandro Lazaric. 414 [doi]
• Dueling Posterior Sampling for Preference-Based Reinforcement LearningEllen R. Novoseller, Yibing Wei, Yanan Sui, Yisong Yue, Joel Burdick. 424 [doi]
• Permutation-Based Causal Structure Learning with Unknown Intervention TargetsChandler Squires, Yuhao Wang 0005, Caroline Uhler. 433 [doi]
• MASSIVE: Tractable and Robust Bayesian Learning of Many-Dimensional Instrumental Variable ModelsIoan Gabriel Bucur, Tom Claassen, Tom Heskes. 439 [doi]
• Popularity Agnostic Evaluation of Knowledge Graph EmbeddingsAisha Mohamed, Shameem Puthiya Parambath, Zoi Kaoudi, Ashraf Aboulnaga. 440 [doi]
• Learning LWF Chain Graphs: A Markov Blanket Discovery ApproachMohammad Ali Javidian, Marco Valtorta, Pooyan Jamshidi. 446 [doi]
• Batch norm with entropic regularization turns deterministic autoencoders into generative modelsAmur Ghose, Abdullah Rashwan, Pascal Poupart. 451 [doi]
• Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect EstimationMarco Morucci, Vittorio Orlandi, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky. 452 [doi]
• Generalized Policy Elimination: an efficient algorithm for Nonparametric Contextual BanditsAurélien Bibaut, Antoine Chambaz, Mark J. van der Laan. 455 [doi]
• Differentially Private Top-k Selection via Stability on Unknown DomainRicardo Silva Carvalho, Ke Wang 0001, Lovedeep Gondara, Chunyan Miao. 459 [doi]
• Active Learning of Conditional Mean Embeddings via Bayesian OptimisationSayak Ray Chowdhury, Rafael Oliveira 0001, Fabio Ramos. 469 [doi]
• Flexible Prior Elicitation via the Prior Predictive DistributionMarcelo Hartmann, Georgi Agiashvili, Paul Bürkner, Arto Klami. 470 [doi]
• Model-Augmented Conditional Mutual Information Estimation for Feature SelectionAlan Yang, AmirEmad Ghassami, Maxim Raginsky, Negar Kiyavash, Elyse Rosenbaum. 474 [doi]
• Finite-Memory Near-Optimal Learning for Markov Decision Processes with Long-Run Average RewardJan Kretínský, Fabian Michel, Lukas Michel, Guillermo A. Pérez. 480 [doi]
• Constraint-Based Causal Discovery using Partial Ancestral Graphs in the presence of CyclesJoris M. Mooij, Tom Claassen. 481 [doi]
• Estimation Rates for Sparse Linear Cyclic Causal ModelsJan-Christian Hütter, Philippe Rigollet. 482 [doi]
• Prediction Intervals: Split Normal Mixture from Quality-Driven Deep EnsemblesTárik S. Salem, Helge Langseth, Heri Ramampiaro. 485 [doi]
• On the Relationship Between Probabilistic Circuits and Determinantal Point ProcessesHonghua Zhang, Steven Holtzen, Guy Van den Broeck. 486 [doi]
• Probabilistic Safety for Bayesian Neural NetworksMatthew Wicker, Luca Laurenti, Andrea Patane, Marta Kwiatkowska. 490 [doi]
• Distortion estimates for approximate Bayesian inferenceHanwen Xing, Geoff Nicholls, Jeong Lee. 496 [doi]
• Mutual Information Based Knowledge Transfer Under State-Action Dimension MismatchMichael Wan, Tanmay Gangwani, Jian Peng 0001. 497 [doi]
• Provably Efficient Third-Person Imitation from Offline ObservationAaron Zweig, Joan Bruna. 500 [doi]
• Automated Dependence PlotsDavid I. Inouye, Liu Leqi, Joon Sik Kim, Bryon Aragam, Pradeep Ravikumar. 503 [doi]
• EiGLasso: Scalable Estimation of Cartesian Product of Sparse Inverse Covariance MatricesJun Ho Yoon, Seyoung Kim. 507 [doi]
• Improved Vector Pruning in Exact Algorithms for Solving POMDPsEric A. Hansen, Thomas Bowman. 509 [doi]
• Symbolic Querying of Vector Spaces: Probabilistic Databases Meets Relational EmbeddingsTal Friedman, Guy Van den Broeck. 512 [doi]
• Learning to learn generative programs with Memoised Wake-SleepLuke B. Hewitt, Tuan Anh Le, Joshua B. Tenenbaum. 517 [doi]
• Flexible Approximate Inference via Stratified Normalizing FlowsChris Cundy, Stefano Ermon. 518 [doi]
• Bounded Rationality in Las Vegas: Probabilistic Finite Automata Play Multi-Armed BanditsXinming Liu, Joseph Y. Halpern. 521 [doi]
• Greedy Policy Search: A Simple Baseline for Learnable Test-Time AugmentationAlexander Lyzhov, Yuliya Molchanova, Arsenii Ashukha, Dmitry Molchanov, Dmitry P. Vetrov. 535 [doi]
• Non Parametric Graph Learning for Bayesian Graph Neural NetworksSoumyasundar Pal, Saber Malekmohammadi, Florence Regol, Yingxue Zhang, Yishi Xu, Mark Coates. 538 [doi]
• Stable Policy Optimization via Off-Policy Divergence RegularizationAhmed Touati, Amy Zhang 0001, Joelle Pineau, Pascal Vincent. 543 [doi]
• PoRB-Nets: Poisson Process Radial Basis Function NetworksBeau Coker, Melanie Fernandes Pradier, Finale Doshi-Velez. 554 [doi]
• Deriving Bounds And Inequality Constraints Using Logical Relations Among CounterfactualsNoam Finkelstein, Ilya Shpitser. 555 [doi]
• Locally Masked Convolution for Autoregressive ModelsAjay Jain, Pieter Abbeel, Deepak Pathak. 565 [doi]
• Time Series Analysis using a Kernel based Multi-Modal Uncertainty Decomposition FrameworkRishabh Singh, José C. Príncipe. 567 [doi]
• OCEAN: Online Task Inference for Compositional Tasks with Context AdaptationHongyu Ren, Yuke Zhu, Jure Leskovec, Animashree Anandkumar, Animesh Garg. 569 [doi]
• Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasetsJakob Runge. 579 [doi]