Accepted papers

  • Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback.
    Marc Jourdan (ETH Zurich); Mojmir Mutny (ETH Zurich); Johannes Kirschner (ETH Zurich); Andreas Krause (ETH Zürich)
  • Attribute-Efficient Learning of Halfspaces with Malicious Noise: Near-Optimal Label Complexity and Noise Tolerance.
    Jie Shen (Stevens Institute of Technology); Chicheng Zhang (University of Arizona)
  • Precise Minimax Regret for Logistic Regression with Categorical Feature Values.
    Philippe Jacquet (INRIA); Gil I Shamir (Google); Wojciech Szpankowski (Purdue University)
  • Stochastic Combinatorial Bandits with Linear Space and Non-Linear Feedback.
    Mridul Agarwal (Purdue University); Vaneet Aggarwal (Purdue University); Chris Quinn (Iowa State University); Abhishek Kumar Umrawal (Purdue University)
  • Uncertainty quantification using martingales for misspecified Gaussian processes.
    Willie Neiswanger (Stanford University); Aaditya Ramdas (Carnegie Mellon University)
  • Optimal Regret Bounds for Generalized Linear Bandits under Parameter Drift.
    Louis Faury (Criteo AI Lab); Yoan Russac (ENS Paris); Marc Abeille (Criteo AI Lab); Clement Calauzenes (Criteo)
  • Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data.
    Di Wang (KAUST); Huanyu Zhang (Cornell University); Marco Gaboradi (Boston University); Jinhui Xu (SUNY Buffalo)
  • Statistical guarantees for generative models without domination.
    Nicolas Schreuder (CREST); Arnak Dalalyan (ENSAE Paris – CREST – IP Paris); Victor-Emmanuel Brunel (ENSAE ParisTech)
  • Sequential prediction under log-loss with side information.
    Alankrita Bhatt (UCSD); Young-Han Kim (UCSD)
  • On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians.
    Ishaq Aden-Ali (McMaster University); Hassan Ashtiani (McMaster University); Gautam Kamath (University of Waterloo)
  • Unexpected Effects of Online no-Substitution k-means Clustering.
    Michal Moshkovitz (UC San Diego)
  • Last Round Convergence and No-Dynamic Regret in Asymmetric Repeated Games.
    Le Cong Dinh (University of Southampton); Tri-Dung Nguyen (University of Southampton); Alain Zemkoho (University of Southampton); Long Tran-Thanh (University of Warwick)
  • Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time.
    Thibaut Cuvelier (CentraleSupelec / Orange Labs); Richard Combes (CentraleSupelec); Eric Gourdin (Orange Labs)
  • Efficient Algorithms for Stochastic Repeated Second-price Auctions.
    Juliette Achddou (ENS Paris); Olivier Cappé (ENS Paris); Aurélien Garivier (ENS Lyon)
  • Contrastive learning, multi-view redundancy, and linear models.
    Christopher Tosh (Columbia University); Akshay Krishnamurthy (Microsoft); Daniel Hsu (Columbia University)
  • Bounding, Concentrating, and Truncating: Unifying Privacy Loss Composition for Data Analytics.
    Mark B Cesar (LinkedIn); Ryan Rogers (LinkedIn)
  • Descent-to-Delete: Gradient-Based Methods for Machine Unlearning.
    Seth Neel (University of Pennsylvania); Aaron Roth (University of Pennsylvania); Saeed Sharifi-Malvajerdi (University of Pennsylvania)
  • Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions.
    Gellert Weisz (DeepMind, UCL); Philip Amortila (); Csaba Szepesvari (DeepMind/University of Alberta)
  • Intervention Efficient Algorithms for Approximate Learning of Causal Graphs.
    Raghavendra Addanki (University of Massachusetts Amherst); Andrew McGregor (University of Massachusetts Amherst); Cameron Musco (University of Massachusetts Amherst)
  • Efficient sampling from the Bingham distribution.
    Rong Ge (Duke University); Holden Lee (Duke); Jianfeng Lu (Duke University); Andrej Risteski (CMU)
  • Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds.
    Ehsan Emamjomeh-Zadeh (University of Southern California); Chen-Yu Wei (University of Southern California); Haipeng Luo (USC); David Kempe (USC)
  • Last-Iterate Convergence Rates for Min-Max Optimization: Convergence of Hamiltonian Gradient Descent and Consensus Optimization.
    Jacob D Abernethy (Georgia Institute of Technolog); Kevin A Lai (Georgia Institute of Technology); Andre Wibisono (Georgia Institute of Technology)
  • No-substitution k-means Clustering with Adversarial Order.
    Robi Bhattacharjee (University of California, San Diego); Michal Moshkovitz (UC San Diego)
  • Adaptive Reward-Free Exploration.
    Emilie Kaufmann (CNRS); Pierre Menard (Inria); Omar Darwiche Domingues (Inria); Anders Jonsson (UPF); Edouard Leurent (Inria / Renault); Michal Valko (DeepMind)
  • Stochastic Dueling Bandits with Adversarial Corruption.
    Arpit Agarwal (University of Pennsylvania); Shivani Agarwal (University of Pennsylvania); Prathamesh Patil (University of Pennsylvania)
  • Characterizing the implicit bias via a primal-dual analysis.
    Ziwei Ji (University of Illinois at Urbana-Champaign); Matus Telgarsky (UIUC)
  • A Deep Conditioning Treatment of Neural Networks.
    Naman Agarwal (Google); Pranjal Awasthi (Rutgers University/Google); Satyen Kale (Google)
  • Online Learning of Facility Locations.
    Stephen U Pasteris (University College London); Ting He (Pennsylvania State University); Fabio Vitale (University of Lille); Shiqiang Wang (IBM Research); Mark Herbster (UCL)
  • Non-uniform Consistency of Online Learning with Random Sampling.
    Changlong Wu (University of Hawaii at Manoa); Narayana Santhanam ()
  • Differentially Private Assouad, Fano, and Le Cam.
    Jayadev Acharya (Cornell University); Ziteng Sun (Cornell University); Huanyu Zhang (Cornell University)
  • An Efficient Algorithm for Cooperative Semi-Bandits.
    Riccardo Della Vecchia (Bocconi University); Tommaso R. Cesari (ANITI / Toulouse School of Economics)
  • Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model.
    Jean Tarbouriech (Facebook AI Research & Inria); Matteo Pirotta (Facebook AI Research); Michal Valko (Inria); Alessandro Lazaric (FAIR)
  • Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited.
    Omar Darwiche Domingues (Inria); Pierre Menard (Inria); Emilie Kaufmann (CNRS); Michal Valko (DeepMind)
  • Subspace Embeddings Under Nonlinear Transformations.
    Aarshvi Gajjar (University of Massachusetts, Amherst); Cameron Musco (University of Massachusetts Amherst)
  • Submodular Combinatorial Information Measures with Applications in Machine Learning.
    Rishabh Iyer (University of Texas at Dallas); Ninad A Khargonkar (University of Texas at Dallas); Jeffrey A Bilmes (University of Washington); Himanshu Asnani (TIFR)
  • Learning a mixture of two subspaces over finite fields.
    Aidao Chen (Northwestern University); Anindya De (University of Pennsylvania); Aravindan Vijayaraghavan (Northwestern University)
  • Near-tight closure bounds for the Littlestone and threshold dimensions.
    Badih Ghazi (Google); Noah Golowich (Massachusetts Institute of Technology); Ravi Kumar (Google); Pasin Manurangsi (Google)
  • Learning and Testing Irreducible Markov Chains via the k-Cover Time.
    Siu On Chan (CUHK); Qinghua Ding (Chinese University of Hong Kong); Sing Hei Li (CUHK)
  • Testing Product Distributions: A Closer Look.
    Arnab Bhattacharyya (National University of Singapore); Sutanu Gayen (National University of SIngapore); Saravanan Kandasamy (Cornell University); N. V. Vinodchandran (University of Nebraska)
  • A case where a spindly two-layer linear network whips any neural network with a fully connected input layer.
    Manfred K. Warmuth (UC Santa Cruz & Google Inc.); Wojciech Kotlowski (Poznan University of Technology); Ehsan Amid (UCSC & Google)
  • Efficient Learning with Arbitrary Covariate Shift.
    Adam Tauman Kalai (Microsoft Research); Varun Kanade (University of Oxford)
  • Online Boosting with Bandit Feedback.
    Nataly Brukhim (Princeton University); Elad Hazan (Princeton University)
  • Self-Tuning Bandits over Unknown Covariate-Shifts.
    Joseph Suk (Columbia University); Samory Kpotufe (Columbia University)
  • Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound.
    Steve Hanneke (Toyota Technological Institute at Chicago); aryeh Kontorovich (Ben-Gurion University)
  • Estimating Sparse Discrete Distributions Under Privacy and Communication Constraints.
    Jayadev Acharya (Cornell University); Peter Kairouz (Google); Yuhan Liu (Cornell); Ziteng Sun (Cornell University)
  • Learning with comparison feedback.
    Michela Meister (Cornell University); Sloan Nietert (Cornell University)