{"total":44,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2202.04690","title":"Smoothed Online Learning is as Easy as Statistical Learning","created":"2022-02-09","cited_by_count":52,"area":null},{"id":"2206.14906","title":"A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback","created":"2022-06-29","cited_by_count":23,"area":null},{"id":"2201.11921","title":"Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits","created":"2022-01-28","cited_by_count":18,"area":null},{"id":"2112.02866","title":"Nonstochastic Bandits with Composite Anonymous Feedback","created":"2021-12-06","cited_by_count":16,"area":null},{"id":"2103.12487","title":"Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2305.17301","title":"Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2206.03098","title":"Better Best of Both Worlds Bounds for Bandits with Switching Costs","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2212.12567","title":"Adapting to game trees in zero-sum imperfect information games","created":"2022-12-23","cited_by_count":11,"area":null},{"id":"2308.10675","title":"A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2403.00715","title":"Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2102.08358","title":"Efficient Competitions and Online Learning with Strategic Forecasters","created":"2021-02-16","cited_by_count":9,"area":null},{"id":"2305.15383","title":"On the Minimax Regret for Online Learning with Feedback Graphs","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2307.02295","title":"Meta-Learning Adversarial Bandit Algorithms","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2405.20678","title":"No-Regret Learning for Fair Multi-Agent Social Welfare Optimization","created":"2024-05-31","cited_by_count":8,"area":null},{"id":"2301.10500","title":"Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning","created":"2023-01-25","cited_by_count":7,"area":null},{"id":"2202.07071","title":"A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2205.14128","title":"Meta-Learning Adversarial Bandits","created":"2022-05-27","cited_by_count":5,"area":null},{"id":"2302.05430","title":"Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making","created":"2023-02-10","cited_by_count":5,"area":null},{"id":"2410.00690","title":"Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2311.02407","title":"The equivalence of dynamic and strategic stability under regularized learning in games","created":"2023-11-04","cited_by_count":4,"area":null},{"id":"2403.01315","title":"Near-optimal Per-Action Regret Bounds for Sleeping Bandits","created":"2024-03-02","cited_by_count":3,"area":null},{"id":"2405.20028","title":"A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2406.16802","title":"Improved Regret Bounds for Bandits with Expert Advice","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2409.20440","title":"Optimism in the Face of Ambiguity Principle for Multi-Armed Bandits","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2508.18604","title":"Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2205.15921","title":"Online Meta-Learning in Adversarial Multi-Armed Bandits","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2312.08008","title":"Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2504.07307","title":"Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2110.13400","title":"Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays","created":"2021-10-26","cited_by_count":1,"area":null},{"id":"2503.02758","title":"Efficient and Optimal No-Regret Caching under Partial Observation","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2505.21790","title":"Faster Rates for Private Adversarial Bandits","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.12490","title":"Note on Follow-the-Perturbed-Leader in Combinatorial Semi-Bandit Problems","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2509.08765","title":"One-shot acceleration of transient PDE solvers via online-learned preconditioners","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2510.12152","title":"Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2510.24187","title":"Self-Concordant Perturbations for Linear Bandits","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.22283","title":"The Hidden Cost of Approximation in Online Mirror Descent","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2305.15331","title":"No-Regret Online Prediction with Strategic Experts","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2310.02246","title":"Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2404.04509","title":"Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2512.08138","title":"Robust equilibria in continuous games: From strategic to dynamic robustness","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2604.05129","title":"No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2608.09389","title":"Regret, equilibrium, and learning in games: A guided tour","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2610.17818","title":"Follow the Perturbed Leader for Linear Bandits: $\\sqrt{T}$ Regret over General Convex Sets","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}