- Online Learning of Quantum States with Logarithmic Loss via VB-FTRL
Wei-Fu Tseng (National Taiwan University), Kai-Chun Chen (National Taiwan University), Zi-Hong Xiao (National Taiwan University), Yen-Huan Li (National Taiwan University)
- Sharp bounds on aggregate expert error
Ariel Avital (Ben Gurion University of the Negev, Technion), Aryeh Kontorovich (Ben Gurion University of the Negev)
- A PAC-Bayesian Link Between Generalisation and Flat Minima
Maxime Haddouche (INRIA), Paul Viallard (INRIA Paris), Umut Simsekli (INRIA), Benjamin Guedj (University College London, University of London)
- A Unified Theory of Supervised Online Learnability
Vinod Raman (University of Michigan – Ann Arbor), Unique Subedi (University of Michigan – Ann Arbor), Ambuj Tewari (University of Michigan – Ann Arbor)
- Generalisation under gradient descent via deterministic PAC-Bayes
Eugenio Clerico (Universitat Pompeu Fabra), Tyler Farghly (University of Oxford), George Deligiannidis (Oxofrd, University of Oxford), Benjamin Guedj (University College London, University of London), Arnaud Doucet (Google DeepMind)
- Boosting, Voting Classifiers and Randomized Sample Compression Schemes
Arthur da Cunha (Aarhus University), Kasper Green Larsen (Aarhus University), Martin Ritzert (Georg-August Universität Göttingen)
- Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate
Jie Shen (Stevens Institute of Technology)
- High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm
Vishwak Srinivasan (Massachusetts Institute of Technology), Andre Wibisono (Yale University), Ashia C. Wilson (Massachusetts Institute of Technology)
- Quantile Multi-Armed Bandits with 1-bit Feedback
Ivan Lau (National University of Singapore), Jonathan Scarlett (National University of Singapore)
- Logarithmic Regret for Unconstrained Submodular Maximization Stochastic Bandit
Julien Zhou (Université Grenoble Alpes), Pierre Gaillard (INRIA), Thibaud Rahier (INRIA), Julyan Arbel (Inria)
- A Characterization of List Regression
Chirag Pabbaraju (Stanford University), Sahasrajit Sarmasarkar (Stanford University)
- Efficient Optimal PAC Learning
Mikael Møller Høgsgaard (Aarhus University)
- Do PAC-Learners Learn the Marginal Distribution?
Max Hopkins (Institue for Advanced Study, Princeton), Daniel Kane (University of California-San Diego), Shachar Lovett (University of California-San Diego), Gaurav Mahajan (Yale University)
- Data Dependent Regret Bounds for Online Portfolio Selection with Predicted Returns
Sudeep Raja Putta (Columbia University), Shipra Agrawal (Columbia University)
- Optimal Rates for O(1)-Smooth DP-SCO with a Single Epoch and Large Batches
Christopher A. Choquette-Choo (Google DeepMind), Arun Ganesh (Google), Abhradeep Guha Thakurta (Google)
- How rotation invariant algorithms are fooled by noise on sparse targets
Manfred K Warmuth (Google Research), Wojciech Kotlowski (Poznan University of Technology), Matt Jones (University of Colorado Boulder), Ehsan Amid (Google DeepMind)
- Understanding Aggregations of Proper Learners in Multiclass Classification
Julian Asilis (University of Southern California), Mikael Møller Høgsgaard (Aarhus University), Grigoris Velegkas (Yale University)
- The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
Matan Schliserman (Tel Aviv University), Uri Sherman (Tel Aviv University), Tomer Koren (Tel Aviv University)
- Clustering with bandit feedback: breaking down the computation/information gap
Thuot Victor (INRAE), Alexandra Carpentier (Universität Potsdam), Christophe Giraud (Université Paris Saclay), Nicolas Verzelen (INRAE)
- Enhanced $H$-Consistency Bounds
Anqi Mao (Courant Institute of Mathematical Sciences, NYU), Mehryar Mohri (New York University), Yutao Zhong (Courant Institute of Mathematical Sciences, NYU)
- Noisy Computing of the Threshold Function
Ziao Wang (University of British Columbia), Nadim Ghaddar (University of Toronto), Banghua Zhu (University of California Berkeley), Lele Wang (University of British Columbia)
- Strategyproof Learning with Advice
Eric Balkanski (Columbia University), Cherlin Zhu (Columbia University)
- Cost-Free Fairness in Online Correlation Clustering
Eric Balkanski (Columbia University), Jason Chatzitheodorou (Columbia University), Andreas Maggiori (Columbia University)
- Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits Problem
Avrim Blum (Toyota Technological Institute at Chicago), Kavya Ravichandran (Toyota Technological Institute at Chicago)
- A Model for Combinatorial Dictionary Learning and Inference
Avrim Blum (Toyota Technological Institute at Chicago), Kavya Ravichandran (Toyota Technological Institute at Chicago)
- Non-stochastic Bandits With Evolving Observations
Yogev Bar-On (Tel Aviv University), Yishay Mansour (School of Computer Science, Tel Aviv University)
- Sample Compression Scheme Reductions
Idan Attias (Ben Gurion University of the Negev), Steve Hanneke (Purdue University), Arvind Ramaswami (Purdue University)
- Fast Convergence of $\Phi$-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler
Siddharth Mitra (Yale University), Andre Wibisono (Yale University)
- Self-Directed Node Classification on Graphs
Georgy Sokolov (Moscow Institute of Physics and Technology), Maximilian Thiessen (TU Wien), Margarita Akhmejanova (King Abdullah University of Science and Technology), Fabio Vitale (CENTAI Institute), Francesco Orabona (King Abdullah University of Science and Technology)
- An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems
Sarah Sachs (Bocconi University), Hedi Hadiji (CentraleSupelec), Tim van Erven (University of Amsterdam), Mathias Staudigl (Universität Mannheim)
- Generalization bounds for mixing processes via delayed online-to-PAC conversions
Baptiste Abélès (Universitat Pompeu Fabra), Eugenio Clerico (Universitat Pompeu Fabra), Gergely Neu (Universitat Pompeu Fabra)
- Minimax Adaptive Boosting for Online Nonparametric Regression
Paul Liautaud (Sorbonne Université – Faculté des Sciences (Paris VI)), Pierre Gaillard (INRIA), Olivier Wintenberger (LPSM)
- Effective Littlestone dimension
Valentino Delle Rose (University of Roma “La Sapienza”), Alexander Kozachinskiy (Pontificia Universidad Catolica de Chile), Tomasz Steifer (Institute of Fundamental Technological Research, Polish Academy of Sciences)
- Reliable Active Apprenticeship Learning
Steve Hanneke (Purdue University), Liu Yang (Data Intelligence Division, China Unicom Digital Technology Co., Ltd.), Gongju Wang (Beijing Jiaotong University), Yulun Song (China Unicom Digital Technology Company)
- Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression
Jackie Lok (Princeton University), Rishi Sonthalia (Boston College), Elizaveta Rebrova (Princeton University)
- Center-Based Approximation of a Drifting Distribution
Alessio Mazzetto (Brown University), Matteo Ceccarello (University of Padua), Andrea Pietracaprina (University of Padua), Geppino Pucci (University of Padua), Eli Upfal (Brown University)
- The Plugin Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis
Matthew Zurek (University of Wisconsin-Madison), Yudong Chen (Department of Computer Sciences, University of Wisconsin – Madison)
- For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent
Steve Hanneke (Purdue University), Amirreza Shaeiri (Sharif University of Technology), Hongao Wang (Purdue University)
- A Complete Characterization of Learnability for Stochastic Noisy Bandits
Kun Wang (Purdue University), Steve Hanneke (Purdue University)
- Refining the Sample Complexity of Comparative Learning
Sajad Rahmanian Ashkezari (York University), Ruth Urner (York University)
- Computationally efficient reductions between some statistical models
Mengqi Lou (Georgia Institute of Technology), Guy Bresler (Massachusetts Institute of Technology), Ashwin Pananjady (Georgia Institute of Technology)
- Agnostic Private Density Estimation for GMMs via List Global Stability
Mohammad Afzali (McMaster University), Hassan Ashtiani (McMaster University), Christopher Liaw (Google)
- On Generalization Bounds for Neural Networks with Low Rank Layers
Andrea Pinto (Massachusetts Institute of Technology), Akshay Rangamani (New Jersey Institute of Technology), Tomaso A Poggio (Massachusetts Institute of Technology)
- When and why randomised exploration works (in linear bandits)
Marc Abeille (Criteo), David Janz (University of Alberta), Ciara Pike-Burke (Imperial College London)
- Differentially Private Multi-Sampling from Distributions
Albert Cheu (Google), Debanuj Nayak (Boston University, Boston University)
- Full Swap Regret and Discretized Calibration
Maxwell Fishelson (Massachusetts Institute of Technology), Robert Kleinberg (Google), Princewill Okoroafor (Department of Computer Science, Cornell University), Renato Paes Leme (Google), Jon Schneider (Google), Yifeng Teng (Google Research)
- Is Transductive Learning Equivalent to PAC Learning?
Shaddin Dughmi (University of Southern California), Yusuf Hakan Kalayci (University of Southern California), Grayson York (University of Southern California)
- Sample Complexity of Recovering Low Rank Tensors from Symmetric Rank-One Measurements
Eren C. Kizildag (University of Illinois at Urbana-Champaign)
- Proper Learnability and the Role of Unlabeled Data
Julian Asilis (University of Southern California), Siddartha Devic (University of Southern California), Shaddin Dughmi (University of Southern California), Vatsal Sharan (University of Southern California), Shang-Hua Teng (University of Southern California)
- Optimal and learned algorithms for the online list update problem with Zipfian accesses
Piotr Indyk (Massachusetts Institute of Technology), Isabelle Quaye (Massachusetts Institute of Technology), Ronitt Rubinfeld (Massachusetts Institute of Technology), Sandeep Silwal (Department of Computer Science, University of Wisconsin – Madison)
- On the Hardness of Learning One Hidden Layer Neural Networks
Shuchen Li (Yale University), Ilias Zadik (Yale University), Manolis Zampetakis (Yale University)