Table of Contents

• Preface and Frontmatter1-11 [doi]
• The neural moving average model for scalable variational inference of state space modelsThomas Ryder, Dennis Prangle, Andrew Golightly, Isaac Matthews. 12-22 [doi]
• Task similarity aware meta learning: theory-inspired improvement on MAMLPan Zhou, Yingtian Zou, Xiao-Tong Yuan, Jiashi Feng, Caiming Xiong, Steven C. H. Hoi. 23-33 [doi]
• Efficient debiased evidence estimation by multilevel Monte Carlo samplingKei Ishikawa, Takashi Goda. 34-43 [doi]
• Variational inference with continuously-indexed normalizing flowsAnthony L. Caterini, Robert Cornish, Dino Sejdinovic, Arnaud Doucet. 44-53 [doi]
• TreeBERT: A tree-based pre-trained model for programming languageXue Jiang, Zhuoran Zheng, Chen Lyu, Liang Li, Lei Lyu. 54-63 [doi]
• Competitive policy optimizationManish Prajapat, Kamyar Azizzadenesheli, Alexander Liniger, Yisong Yue, Anima Anandkumar. 64-74 [doi]
• Improving uncertainty calibration of deep neural networks via truth discovery and geometric optimizationChunwei Ma, Ziyun Huang, Jiayi Xian, Mingchen Gao, Jinhui Xu 0001. 75-85 [doi]
• Incorporating causal graphical prior knowledge into predictive modeling via simple data augmentationTakeshi Teshima, Masashi Sugiyama. 86-96 [doi]
• Causal additive models with unobserved variablesTakashi Nicholas Maeda, Shohei Shimizu. 97-106 [doi]
• A variational approximation for analyzing the dynamics of panel dataJurijs Nazarovs, Rudrasis Chakraborty, Songwong Tasneeyapant, Sathya N. Ravi, Vikas Singh. 107-117 [doi]
• Graph reparameterizations for enabling 1000+ Monte Carlo iterations in Bayesian deep neural networksJurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh. 118-128 [doi]
• The curious case of adversarially robust models: More data can help, double descend, or hurt generalizationYifei Min, Lin Chen 0003, Amin Karbasi. 129-139 [doi]
• Contrastive prototype learning with augmented embeddings for few-shot learningYizhao Gao, Nanyi Fei, Guangzhen Liu, Zhiwu Lu 0001, Tao Xiang. 140-150 [doi]
• XOR-SGD: provable convex stochastic optimization for decision-making under uncertaintyFan Ding, Yexiang Xue. 151-160 [doi]
• Path dependent structural equation modelsRanjani Srinivasan, Jaron J. R. Lee, Rohit Bhattacharya, Ilya Shpitser. 161-171 [doi]
• Featurized density ratio estimationKristy Choi, Madeline Liao, Stefano Ermon. 172-182 [doi]
• Variance reduction in frequency estimators via control variates methodRameshwar Pratap, Raghav Kulkarni. 183-193 [doi]
• Application of kernel hypothesis testing on set-valued dataAlexis Bellot, Mihaela van der Schaar. 194-204 [doi]
• A kernel two-sample test with selection biasAlexis Bellot, Mihaela van der Schaar. 205-214 [doi]
• An unsupervised video game playstyle metric via state discretizationChiu-Chou Lin, Wei-chen Chiu, I-Chen Wu. 215-224 [doi]
• Most: multi-source domain adaptation via optimal transport for student-teacher learningTuan Nguyen, Trung Le, He Zhao 0001, Quan Hung Tran, Truyen Nguyen, Dinh Q. Phung. 225-235 [doi]
• Constrained labeling for weakly supervised learningChidubem Arachie, Bert Huang. 236-246 [doi]
• Communication efficient parallel reinforcement learningMridul Agarwal, Bhargav Ganguly, Vaneet Aggarwal. 247-256 [doi]
• Robust reinforcement learning under minimax regret for green securityLily Xu, Andrew Perrault, Fei Fang, Haipeng Chen, Milind Tambe. 257-267 [doi]
• Defending SVMs against poisoning attacks: the hardness and DBSCAN approachHu Ding, Fan Yang, Jiawei Huang. 268-278 [doi]
• Matrix games with bandit feedbackBrendan O'Donoghue, Tor Lattimore, Ian Osband. 279-289 [doi]
• Improving approximate optimal transport distances using quantizationGaspard Beugnot, Aude Genevay, Kristjan H. Greenewald, Justin Solomon 0001. 290-300 [doi]
• Approximate implication with d-separationBatya Kenig. 301-311 [doi]
• Hierarchical probabilistic model for blind source separation via Legendre transformationSimon Luo, Lamiae Azizi, Mahito Sugiyama. 312-321 [doi]
• Lifted reasoning meets weighted model integrationJonathan Feldstein, Vaishak Belle. 322-332 [doi]
• Formal verification of neural networks for safety-critical tasks in deep reinforcement learningDavide Corsi, Enrico Marchesini, Alessandro Farinelli. 333-343 [doi]
• Learnable uncertainty under Laplace approximationsAgustinus Kristiadi, Matthias Hein 0001, Philipp Hennig. 344-353 [doi]
• Symmetric Wasserstein autoencodersSun Sun, Hongyu Guo. 354-364 [doi]
• Unsupervised anomaly detection with adversarial mirrored autoencodersGowthami Somepalli, Yexin Wu, Yogesh Balaji, Bhanukiran Vinzamuri, Soheil Feizi. 365-375 [doi]
• Action redundancy in reinforcement learningNir Baram, Guy Tennenholtz, Shie Mannor. 376-385 [doi]
• Weighted model counting with conditional weights for Bayesian networksPaulius Dilkas, Vaishak Belle. 386-396 [doi]
• Escaping from zero gradient: Revisiting action-constrained reinforcement learning via Frank-Wolfe policy optimizationJyun-Li Lin, Wei Hung, Shang-Hsuan Yang, Ping-Chun Hsieh, Xi Liu 0011. 397-407 [doi]
• Unsupervised program synthesis for images by sampling without replacementChenghui Zhou, Chun-Liang Li, Barnabás Póczos. 408-418 [doi]
• On the distributional properties of adaptive gradientsZhiyi Zhang, Ziyin Liu. 419-429 [doi]
• Bandits with partially observable confounded dataGuy Tennenholtz, Uri Shalit, Shie Mannor, Yonathan Efroni. 430-439 [doi]
• Structured sparsification with joint optimization of group convolution and channel shuffleXin-yu Zhang, Kai Zhao, Taihong Xiao, Ming-Ming Cheng, Ming-Hsuan Yang 0001. 440-450 [doi]
• A weaker faithfulness assumption based on triple interactionsAlexander Marx, Arthur Gretton, Joris M. Mooij. 451-460 [doi]
• pRSL: Interpretable multi-label stacking by learning probabilistic rulesMichael Kirchhof, Lena Schmid, Christopher Reining, Michael ten Hompel, Markus Pauly. 461-470 [doi]
• Regstar: efficient strategy synthesis for adversarial patrolling gamesDavid Klaska, Antonín Kucera 0001, Vít Musil, Vojtech Rehák. 471-481 [doi]
• The complexity of nonconvex-strongly-concave minimax optimizationSiqi Zhang, Junchi Yang, Cristóbal Guzmán, Negar Kiyavash, Niao He. 482-492 [doi]
• High-dimensional Bayesian optimization with sparse axis-aligned subspacesDavid Eriksson, Martin Jankowiak. 493-503 [doi]
• Known unknowns: Learning novel concepts using reasoning-by-eliminationHarsh Agrawal, Eli A. Meirom, Yuval Atzmon, Shie Mannor, Gal Chechik. 504-514 [doi]
• Dynamic visualization for L1 fusion convex clustering in near-linear timeBingyuan Zhang, Jie Chen, Yoshikazu Terada. 515-524 [doi]
• FlexAE: flexibly learning latent priors for wasserstein auto-encodersArnab Kumar Mondal, Himanshu Asnani, Parag Singla, A. P. Prathosh. 525-535 [doi]
• Generalized parametric path problemsKshitij Gajjar, Girish Varma, Prerona Chatterjee, Jaikumar Radhakrishnan. 536-546 [doi]
• Efficient greedy coordinate descent via variable partitioningHuang Fang, Guanhua Fang, Tan Yu, Ping Li 0001. 547-557 [doi]
• Bayesian streaming sparse Tucker decompositionShikai Fang, Robert M. Kirby, Shandian Zhe. 558-567 [doi]
• A Nonmyopic Approach to Cost-Constrained Bayesian OptimizationEric Hans Lee, David Eriksson, Valerio Perrone, Matthias W. Seeger. 568-577 [doi]
• Asynchronous ε-Greedy Bayesian OptimisationGeorge De Ath, Richard M. Everson, Jonathan E. Fieldsend. 578-588 [doi]
• Global explanations with decision rules: a co-learning approachGéraldin Nanfack, Paul Temple, Benoît Frénay. 589-599 [doi]
• Addressing fairness in classification with a model-agnostic multi-objective algorithmKirtan Padh, Diego Antognini, Emma Lejal Glaude, Boi Faltings, Claudiu Musat. 600-609 [doi]
• A unifying framework for observer-aware planning and its complexityShuwa Miura, Shlomo Zilberstein. 610-620 [doi]
• A heuristic for statistical seriationKomal Dhull, Jingyan Wang 0001, Nihar B. Shah, Yuanzhi Li, R. Ravi 0001. 621-631 [doi]
• LocalNewton: Reducing communication rounds for distributed learningVipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Kannan Ramchandran, Michael W. Mahoney. 632-642 [doi]
• Generative Archimedean copulasYuting Ng, Ali-Hasan, Khalil Elkhalil, Vahid Tarokh. 643-653 [doi]
• Exploring the loss landscape in neural architecture searchColin White, Sam Nolen, Yash Savani. 654-664 [doi]
• Finite-time theory for momentum Q-learningBowen Weng, Huaqing Xiong, Lin Zhao, Yingbin Liang, Wei Zhang. 665-674 [doi]
• Scaling Hamiltonian Monte Carlo inference for Bayesian neural networks with symmetric splittingAdam D. Cobb, Brian Jalaian. 675-685 [doi]
• Robust principal component analysis for generalized multi-view modelsFrank Nussbaum, Joachim Giesen. 686-695 [doi]
• Decentralized multi-agent active search for sparse signalsRamina Ghods, Arundhati Banerjee, Jeff Schneider. 696-706 [doi]
• Unbiased gradient estimation for variational auto-encoders using coupled Markov chainsFrancisco J. R. Ruiz, Michalis K. Titsias, A. Taylan Cemgil, Arnaud Doucet. 707-717 [doi]
• Possibilistic preference elicitation by minimax regretLoïc Adam, Sébastien Destercke. 718-727 [doi]
• When is particle filtering efficient for planning in partially observed linear dynamical systems?Simon S. Du, Wei Hu, Zhiyuan Li 0005, Ruoqi Shen, Zhao Song 0002, Jiajun Wu 0001. 728-737 [doi]
• Thompson sampling for Markov games with piecewise stationary opponent policiesAnthony DiGiovanni, Ambuj Tewari. 738-748 [doi]
• Hierarchical Indian buffet neural networks for Bayesian continual learningSamuel Kessler, Vu Nguyen, Stefan Zohren, Stephen J. Roberts. 749-759 [doi]
• Measuring data leakage in machine-learning models with Fisher informationAwni Y. Hannun, Chuan Guo, Laurens van der Maaten. 760-770 [doi]
• Improved generalization bounds of group invariant / equivariant deep networks via quotient feature spacesAkiyoshi Sannai, Masaaki Imaizumi, Makoto Kawano. 771-780 [doi]
• Probabilistic task modelling for meta-learningCuong C. Nguyen, Thanh-Toan Do, Gustavo Carneiro. 781-791 [doi]
• Approximation algorithm for submodular maximization under submodular coverNaoto Ohsaka, Tatsuya Matsuoka. 792-801 [doi]
• Tighter Generalization Bounds for Iterative Differentially Private Learning AlgorithmsFengxiang He, Bohan Wang, Dacheng Tao. 802-812 [doi]
• Dependency in DAG models with hidden variablesRobin J. Evans. 813-822 [doi]
• Natural language adversarial defense through synonym encodingXiaosen Wang, Jin Hao, Yichen Yang 0009, Kun He 0001. 823-833 [doi]
• Path-BN: Towards effective batch normalization in the Path Space for ReLU networksXufang Luo, Qi Meng, Wei Chen, Yunhong Wang, Tie-Yan Liu. 834-843 [doi]
• Distribution-free uncertainty quantification for classification under label shiftAleksandr Podkopaev, Aaditya Ramdas. 844-853 [doi]
• Identifying untrustworthy predictions in neural networks by geometric gradient analysisLeo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger 0001, Björn M. Eskofier. 854-864 [doi]
• Combinatorial semi-bandit in the non-stationary environmentWei Chen, Liwei Wang, Haoyu Zhao, Kai Zheng. 865-875 [doi]
• Time-variant variational transfer for value functionsGiuseppe Canonaco, Andrea Soprani, Matteo Giuliani, Andrea Castelletti, Manuel Roveri, Marcello Restelli. 876-886 [doi]
• BayLIME: Bayesian local interpretable model-agnostic explanationsXingyu Zhao 0001, Wei Huang, Xiaowei Huang 0001, Valentin Robu, David Flynn. 887-896 [doi]
• On random kernels of residual architecturesEtai Littwin, Tomer Galanti, Lior Wolf. 897-907 [doi]
• Neural markov logic networksGiuseppe Marra, Ondrej Kuzelka. 908-917 [doi]
• Deep kernels with probabilistic embeddings for small-data learningAnkur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, Thomas Yong-Jin Han. 918-928 [doi]
• On the effects of quantisation on model uncertainty in Bayesian neural networksMartin Ferianc, Partha Maji, Matthew Mattina, Miguel Rodrigues. 929-938 [doi]
• GP-ConvCNP: Better generalization for conditional convolutional Neural Processes on time series dataJens Petersen, Gregor Köhler, David Zimmerer, Fabian Isensee, Paul F. Jäger, Klaus H. Maier-Hein. 939-949 [doi]
• Mixed variable Bayesian optimization with frequency modulated kernelsChangYong Oh, Efstratios Gavves, Max Welling. 950-960 [doi]
• Subseasonal climate prediction in the western US using Bayesian spatial modelsVishwak Srinivasan, Justin Khim, Arindam Banerjee 0001, Pradeep Ravikumar. 961-970 [doi]
• variational combinatorial sequential monte carlo methods for bayesian phylogenetic inferenceAntonio Khalil Moretti, Liyi Zhang, Christian A. Naesseth, Hadiah Venner, David M. Blei, Itsik Pe'er. 971-981 [doi]
• Estimating treatment effects with observed confounders and mediatorsShantanu Gupta, Zachary C. Lipton, David Childers. 982-991 [doi]
• No-regret learning with high-probability in adversarial Markov decision processesMahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu. 992-1001 [doi]
• A decentralized policy gradient approach to multi-task reinforcement learningSihan Zeng, Malik Aqeel Anwar, Thinh T. Doan 0001, Arijit Raychowdhury, Justin Romberg. 1002-1012 [doi]
• Compositional abstraction error and a category of causal modelsEigil Fjeldgren Rischel, Sebastian Weichwald. 1013-1023 [doi]
• Bayesian optimization for modular black-box systems with switching costsChi-Heng Lin, Joseph D. Miano, Eva L. Dyer. 1024-1034 [doi]
• Probabilistic selection of inducing points in sparse Gaussian processesAnders Kirk Uhrenholt, Valentin Charvet, Bjørn Sand Jensen. 1035-1044 [doi]
• Entropic Inequality Constraints from e-separation Relations in Directed Acyclic Graphs with Hidden VariablesNoam Finkelstein, Beata Zjawin, Elie Wolfe, Ilya Shpitser, Robert W. Spekkens. 1045-1055 [doi]
• Learning proposals for probabilistic programs with inference combinatorsSam Stites, Heiko Zimmermann, Hao Wu 0020, Eli Sennesh, Jan-Willem van de Meent. 1056-1066 [doi]
• Hierarchical infinite relational modelFeras A. Saad, Vikash K. Mansinghka. 1067-1077 [doi]
• Unsupervised constrained community detection via self-expressive graph neural networkSambaran Bandyopadhyay, Vishal Peter. 1078-1088 [doi]
• NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image GenerationXiaohui Zeng, Raquel Urtasun, Richard S. Zemel, Sanja Fidler, Renjie Liao. 1089-1099 [doi]
• PALM: Probabilistic area loss Minimization for Protein Sequence AlignmentFan Ding, Nan Jiang, Jianzhu Ma, Jian Peng 0001, Jinbo Xu, Yexiang Xue. 1100-1109 [doi]
• Principal component analysis in the stochastic differential privacy modelFanhua Shang, Zhihui Zhang, Tao Xu, Yuanyuan Liu 0001, Hongying Liu. 1110-1119 [doi]
• Variance-dependent best arm identificationPinyan Lu, Chao Tao, Xiaojin Zhang 0002. 1120-1129 [doi]
• Stochastic continuous normalizing flows: training SDEs as ODEsLiam Hodgkinson, Christopher van der Heide, Fred Roosta, Michael W. Mahoney. 1130-1140 [doi]
• On the distribution of penultimate activations of classification networksMinkyo Seo, Yoonho Lee 0001, Suha Kwak. 1141-1151 [doi]
• Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave SamplingDifan Zou, Pan Xu 0002, Quanquan Gu. 1152-1162 [doi]
• Tractable computation of expected kernelsWenzhe Li, Zhe Zeng, Antonio Vergari, Guy Van den Broeck. 1163-1173 [doi]
• Sparse linear networks with a fixed butterfly structure: theory and practiceNir Ailon, Omer Leibovitch, Vineet Nair. 1174-1184 [doi]
• Uncertainty-aware sensitivity analysis using Rényi divergencesTopi Paananen, Michael Riis Andersen, Aki Vehtari. 1185-1194 [doi]
• Testification of Condorcet Winners in dueling banditsBjörn Haddenhorst, Viktor Bengs, Jasmin Brandt, Eyke Hüllermeier. 1195-1205 [doi]
• The promises and pitfalls of deep kernel learningSebastian W. Ober, Carl E. Rasmussen, Mark van der Wilk. 1206-1216 [doi]
• Confidence in causal discovery with linear causal modelsDavid Strieder, Tobias Freidling, Stefan Haffner, Mathias Drton. 1217-1226 [doi]
• Classification with abstention but without disparitiesNicolas Schreuder, Evgenii Chzhen. 1227-1236 [doi]
• Maximal ancestral graph structure learning via exact searchKari Rantanen, Antti Hyttinen, Matti Järvisalo. 1237-1247 [doi]
• Extendability of causal graphical models: Algorithms and computational complexityMarcel Wienöbst, Max Bannach, Maciej Liskiewicz. 1248-1257 [doi]
• Gaussian process nowcasting: application to COVID-19 mortality reportingIwona Hawryluk, Henrique Hoeltgebaum, Swapnil Mishra, Xenia Miscouridou, Ricardo P. Schnekenberg, Charles Whittaker, Michaela A. C. Vollmer, Seth Flaxman, Samir Bhatt, Thomas A. Mellan. 1258-1268 [doi]
• Trumpets: Injective flows for inference and inverse problemsKonik Kothari, AmirEhsan Khorashadizadeh, Maarten V. De Hoop, Ivan Dokmanic. 1269-1278 [doi]
• Stochastic model for sunk cost biasJon M. Kleinberg, Sigal Oren, Manish Raghavan, Nadav Sklar. 1279-1288 [doi]
• Optimized auxiliary particle filters: adapting mixture proposals via convex optimizationNicola Branchini, V'ictor Elvira. 1289-1299 [doi]
• Inference of causal effects when control variables are unknownLudvig Hult, Dave Zachariah. 1300-1309 [doi]
• Dimension reduction for data with heterogeneous missingnessYurong Ling, Zijing Liu, Jing-Hao Xue. 1310-1320 [doi]
• Tensor-train density estimationGeorgii S. Novikov, Maxim E. Panov, Ivan V. Oseledets. 1321-1331 [doi]
• Similarity measure for sparse time course data based on Gaussian processesZijing Liu, Mauricio Barahona. 1332-1341 [doi]
• Towards robust episodic meta-learningBeyza Ermis, Giovanni Zappella, Cédric Archambeau. 1342-1351 [doi]
• ReZero is all you need: fast convergence at large depthThomas Bachlechner, Bodhisattwa Prasad Majumder, Huanru Henry Mao, Gary Cottrell, Julian McAuley. 1352-1361 [doi]
• Subset-of-data variational inference for deep Gaussian-processes regressionAyush Jain, P. K. Srijith, Mohammad Emtiyaz Khan. 1362-1370 [doi]
• PLSO: A generative framework for decomposing nonstationary time-series into piecewise stationary oscillatory componentsAndrew H. Song, Demba Ba, Emery N. Brown. 1371-1381 [doi]
• Local explanations via necessity and sufficiency: unifying theory and practiceDavid S. Watson, Limor Gultchin, Ankur Taly, Luciano Floridi. 1382-1392 [doi]
• Faster lifting for two-variable logic using cell graphsTimothy van Bremen, Ondrej Kuzelka. 1393-1402 [doi]
• Post-hoc loss-calibration for Bayesian neural networksMeet P. Vadera, Soumya Ghosh, Kenney Ng, Benjamin M. Marlin. 1403-1412 [doi]
• Towards tractable optimism in model-based reinforcement learningAldo Pacchiano, Philip Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts. 1413-1423 [doi]
• Probabilistic DAG searchJulia Grosse, Cheng Zhang, Philipp Hennig. 1424-1433 [doi]
• Causal and interventional Markov boundariesSofia Triantafillou, Fattaneh Jabbari, Gregory F. Cooper. 1434-1443 [doi]
• Simple combinatorial algorithms for combinatorial bandits: corruptions and approximationsHaike Xu, Jian Li. 1444-1454 [doi]
• CLAIM: curriculum learning policy for influence maximization in unknown social networksDexun Li, Meghna Lowalekar, Pradeep Varakantham. 1455-1465 [doi]
• Learning to learn with Gaussian processesQuoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet. 1466-1475 [doi]
• Sum-product laws and efficient algorithms for imprecise Markov chainsJasper De Bock, Alexander Erreygers, Thomas Krak. 1476-1485 [doi]
• Trusted-maximizers entropy search for efficient Bayesian optimizationQuoc Phong Nguyen, Zhaoxuan Wu, Bryan Kian Hsiang Low, Patrick Jaillet. 1486-1495 [doi]
• Minimax sample complexity for turn-based stochastic gameQiwen Cui, Lin F. Yang. 1496-1504 [doi]
• Multi-output Gaussian Processes for uncertainty-aware recommender systemsYinchong Yang, Florian Buettner. 1505-1514 [doi]
• Generalization error bounds for deep unfolding RNNsBoris Joukovsky, Tanmoy Mukherjee, Huynh Van Luong, Nikos Deligiannis. 1515-1524 [doi]
• RISAN: Robust instance specific deep abstention networkBhavya Kalra, Kulin Shah, Naresh Manwani. 1525-1534 [doi]
• Contingency-aware influence maximization: A reinforcement learning approachHaipeng Chen, Wei Qiu 0001, Han-Ching Ou, Bo An 0001, Milind Tambe. 1535-1545 [doi]
• Invariant representation learning for treatment effect estimationClaudia Shi, Victor Veitch, David M. Blei. 1546-1555 [doi]
• Generating adversarial examples with graph neural networksFlorian Jaeckle, M. Pawan Kumar. 1556-1564 [doi]
• A Bayesian nonparametric conditional two-sample test with an application to Local Causal DiscoveryPhilip A. Boeken, Joris M. Mooij. 1565-1575 [doi]
• Graph-based semi-supervised learning through the lens of safetyShreyas Sheshadri, Avirup Saha, Priyank Patel, Samik Datta, Niloy Ganguly. 1576-1586 [doi]
• Strategically efficient exploration in competitive multi-agent reinforcement learningRobert Loftin, Aadirupa Saha, Sam Devlin, Katja Hofmann. 1587-1596 [doi]
• Information theoretic meta learning with Gaussian processesMichalis K. Titsias, Francisco J. R. Ruiz, Sotirios Nikoloutsopoulos, Alexandre Galashov. 1597-1606 [doi]
• Combining pseudo-point and state space approximations for sum-separable Gaussian ProcessesWill Tebbutt, Arno Solin, Richard E. Turner. 1607-1617 [doi]
• Class balancing GAN with a classifier in the loopHarsh Rangwani, Konda Reddy Mopuri, R. Venkatesh Babu. 1618-1627 [doi]
• Hierarchical learning of Hidden Markov Models with clustering regularizationHui Lan, Antoni B. Chan. 1628-1638 [doi]
• Enabling long-range exploration in minimization of multimodal functionsJiaxin Zhang 0005, Hoang Tran, Dan Lu 0001, Guannan Zhang. 1639-1649 [doi]
• An optimization and generalization analysis for max-pooling networksAlon Brutzkus, Amir Globerson. 1650-1660 [doi]
• Investigating vulnerabilities of deep neural policiesEzgi Korkmaz. 1661-1670 [doi]
• Modeling financial uncertainty with multivariate temporal entropy-based curriculumsRamit Sawhney, Arnav Wadhwa, Ayush Mangal, Vivek Mittal, Shivam Agarwal, Rajiv Ratn Shah. 1671-1681 [doi]
• Random probabilistic circuitsNicola Di Mauro, Gennaro Gala, Marco Iannotta, Teresa M. A. Basile. 1682-1691 [doi]
• Multi-task and meta-learning with sparse linear banditsLeonardo Cella, Massimiliano Pontil. 1692-1702 [doi]
• Federated stochastic gradient Langevin dynamicsKhaoula el Mekkaoui, Diego Mesquita, Paul Blomstedt, Samuel Kaski. 1703-1712 [doi]
• Certification of iterative predictions in Bayesian neural networksMatthew Wicker, Luca Laurenti, Andrea Patane, Nicola Paoletti, Alessandro Abate, Marta Kwiatkowska. 1713-1723 [doi]
• Integer programming-based error-correcting output code design for robust classificationSamarth Gupta, Saurabh Amin. 1724-1734 [doi]
• Statistically robust neural network classificationBenjie Wang, Stefan Webb, Tom Rainforth. 1735-1745 [doi]
• Markov equivalence of max-linear Bayesian networksCarlos Améndola, Benjamin Hollering, Seth Sullivant, Ngoc Tran. 1746-1755 [doi]
• Constrained differentially private federated learning for low-bandwidth devicesRaouf Kerkouche, Gergely Ács, Claude Castelluccia, Pierre Genevès. 1756-1765 [doi]
• Know your limits: Uncertainty estimation with ReLU classifiers fails at reliable OOD detectionDennis Ulmer, Giovanni Cinà. 1766-1776 [doi]
• Nearest neighbor search under uncertaintyBlake Mason, Ardhendu Tripathy, Robert Nowak 0001. 1777-1786 [doi]
• Contextual policy transfer in reinforcement learning domains via deep mixtures-of-expertsMichael Gimelfarb, Scott Sanner, Chi-Guhn Lee. 1787-1797 [doi]
• Partial Identifiability in Discrete Data with Measurement ErrorNoam Finkelstein, Roy Adams, Suchi Saria, Ilya Shpitser. 1798-1808 [doi]
• Bias-corrected peaks-over-threshold estimation of the CVaRDylan Troop, Fr'ed'eric Godin, Jia Yuan Yu. 1809-1818 [doi]
• Variational refinement for importance sampling using the forward Kullback-Leibler divergenceGhassen Jerfel, Serena Wang, Clara Wong-Fannjiang, Katherine A. Heller, Yian Ma, Michael I. Jordan. 1819-1829 [doi]
• Diagnostics for conditional density models and Bayesian inference algorithmsDavid Zhao, Niccolò Dalmasso, Rafael Izbicki, Ann B. Lee. 1830-1840 [doi]
• Non-PSD matrix sketching with applications to regression and optimizationZhili Feng, Fred Roosta, David P. Woodruff. 1841-1851 [doi]
• Staying in shape: learning invariant shape representations using contrastive learningJeffrey Gu, Serena Yeung. 1852-1862 [doi]
• Convergence behavior of belief propagation: estimating regions of attraction via Lyapunov functionsHarald Leisenberger, Christian Knoll, Richard Seeber, Franz Pernkopf. 1863-1873 [doi]
• Explaining fast improvement in online imitation learningXinyan Yan, Byron Boots, Ching-An Cheng. 1874-1884 [doi]
• Gradient-based optimization for multi-resource spatial coverage problemsNitin Kamra, Yan Liu. 1885-1894 [doi]
• Doubly non-central beta matrix factorization for DNA methylation dataAaron Schein, Anjali Nagulpally, Hanna Wallach, Patrick Flaherty. 1895-1904 [doi]
• SGD with low-dimensional gradients with applications to private and distributed learningShiva Prasad Kasiviswanathan. 1905-1915 [doi]
• Active multi-fidelity Bayesian online changepoint detectionGregory W. Gundersen, Diana Cai, Chuteng Zhou, Barbara E. Engelhardt, Ryan P. Adams. 1916-1926 [doi]
• Learning in Multi-Player Stochastic GamesWilliam Brown. 1927-1937 [doi]
• q-Paths: Generalizing the geometric annealing path using power meansVaden Masrani, Rob Brekelmans, Thang Bui, Frank Nielsen, Aram Galstyan, Greg Ver Steeg, Frank Wood. 1938-1947 [doi]
• Condition number bounds for causal inferenceSpencer L. Gordon, Vinayak M. Kumar, Leonard J. Schulman, Piyush Srivastava. 1948-1957 [doi]
• Sketching curvature for efficient out-of-distribution detection for deep neural networksApoorva Sharma, Navid Azizan, Marco Pavone. 1958-1967 [doi]
• CORe: Capitalizing On Rewards in Bandit ExplorationNan Wang, Branislav Kveton, Maryam Karimzadehgan. 1968-1978 [doi]
• Explicit pairwise factorized graph neural network for semi-supervised node classificationYu Wang, Yuesong Shen, Daniel Cremers. 1979-1987 [doi]
• Statistical mechanical analysis of neural network pruningRupam Acharyya, Ankani Chattoraj, Boyu Zhang, Shouman Das, Daniel Stefankovic. 1988-1997 [doi]
• Correlated weights in infinite limits of deep convolutional neural networksAdrià Garriga-Alonso, Mark van der Wilk. 1998-2007 [doi]
• Leveraging probabilistic circuits for nonparametric multi-output regressionZhongjie Yu 0001, Mingye Zhu, Martin Trapp 0001, Arseny Skryagin, Kristian Kersting. 2008-2018 [doi]
• PROVIDE: a probabilistic framework for unsupervised video decompositionPolina Zablotskaia, Edoardo A. Dominici, Leonid Sigal, Andreas M. Lehrmann. 2019-2028 [doi]
• Uncertainty in minimum cost multicuts for image and motion segmentationAmirhossein Kardoost, Margret Keuper. 2029-2038 [doi]
• Learning probabilistic sentential decision diagrams under logic constraints by sampling and averagingRenato Lui Geh, Denis Deratani Mau'a. 2039-2049 [doi]
• Conditionally independent data generationKartik Ahuja, Prasanna Sattigeri, Karthikeyan Shanmugam, Dennis Wei, Karthikeyan Natesan Ramamurthy, Murat Kocaoglu. 2050-2060 [doi]
• Exact and approximate hierarchical clustering using ACraig S. Greenberg, Sebastian Macaluso, Nicholas Monath, Avinava Dubey, Patrick Flaherty, Manzil Zaheer, Amr Ahmed, Kyle Cranmer, Andrew McCallum. 2061-2071 [doi]
• Efficient online inference for nonparametric mixture modelsRylan Schaeffer, Blake Bordelon, Mikail Khona, Weiwei Pan, Ila Rani Fiete. 2072-2081 [doi]
• No-regret approximate inference via Bayesian optimisationRafael Oliveira 0001, Lionel Ott, Fabio Ramos. 2082-2092 [doi]
• Disentangling mixtures of unknown causal interventionsAbhinav Kumar, Gaurav Sinha. 2093-2102 [doi]
• SDM-Net: A simple and effective model for generalized zero-shot learningShabnam Daghaghi, Tharun Medini, Anshumali Shrivastava. 2103-2113 [doi]
• Towards a unified framework for fair and stable graph representation learningChirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik. 2114-2124 [doi]
• Identifying regions of trusted predictionsNivasini Ananthakrishnan, Shai Ben-David, Tosca Lechner, Ruth Urner. 2125-2134 [doi]
• Learning and certification under instance-targeted poisoningJi Gao, Amin Karbasi, Mohammad Mahmoody. 2135-2145 [doi]
• Min/max stability and box distributionsMichael Boratko, Javier Burroni, Shib Sankar Dasgupta, Andrew McCallum. 2146-2155 [doi]
• Geometric rates of convergence for kernel-based sampling algorithmsRajiv Khanna, Liam Hodgkinson, Michael W. Mahoney. 2156-2164 [doi]
• Sequential core-set Monte CarloBoyan Beronov, Christian Weilbach, Frank Wood, Trevor Campbell. 2165-2175 [doi]