{"total":114,"rows":[{"id":"2108.06924","title":"Near-Optimal No-Regret Learning in General Games","created":"2021-08-16","cited_by_count":85,"area":null},{"id":"2112.14368","title":"Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization","created":"2021-12-29","cited_by_count":66,"area":null},{"id":"2102.01046","title":"Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications","created":"2021-02-01","cited_by_count":52,"area":null},{"id":"2102.05858","title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","created":"2021-02-11","cited_by_count":48,"area":null},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"area":null},{"id":"2106.04117","title":"The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition","created":"2021-06-08","cited_by_count":40,"area":null},{"id":"2112.03432","title":"First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach","created":"2021-12-07","cited_by_count":38,"area":null},{"id":"2204.11417","title":"Uncoupled Learning Dynamics with $O(\\log T)$ Swap Regret in Multiplayer Games","created":"2022-04-25","cited_by_count":35,"area":null},{"id":"2302.09739","title":"A Blackbox Approach to Best of Both Worlds in Bandits and Beyond","created":"2023-02-20","cited_by_count":30,"area":null},{"id":"2206.00873","title":"Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs","created":"2022-06-02","cited_by_count":26,"area":null},{"id":"2206.08742","title":"Near-Optimal No-Regret Learning Dynamics for General Convex Games","created":"2022-06-17","cited_by_count":25,"area":null},{"id":"2207.14211","title":"Regret Minimization and Convergence to Equilibria in General-sum Markov Games","created":"2022-07-28","cited_by_count":24,"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":"2109.10963","title":"On Optimal Robustness to Adversarial Corruption in Online Decision Problems","created":"2021-09-22","cited_by_count":21,"area":null},{"id":"2111.14737","title":"Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update","created":"2021-11-29","cited_by_count":20,"area":null},{"id":"2102.09864","title":"An Algorithm for Stochastic and Adversarial Bandits with Switching Costs","created":"2021-02-19","cited_by_count":19,"area":null},{"id":"2207.14550","title":"Best-of-Both-Worlds Algorithms for Partial Monitoring","created":"2022-07-29","cited_by_count":19,"area":null},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19,"area":null},{"id":"2309.00814","title":"Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits","created":"2023-09-02","cited_by_count":19,"area":null},{"id":"2111.01589","title":"Nonstochastic Bandits and Experts with Arm-Dependent Delays","created":"2021-11-02","cited_by_count":18,"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":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2206.00557","title":"A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs","created":"2022-06-01","cited_by_count":17,"area":null},{"id":"2302.09408","title":"Best of Both Worlds Policy Optimization","created":"2023-02-18","cited_by_count":17,"area":null},{"id":"2111.08911","title":"Fast Rates for Nonparametric Online Learning: From Realizability to Learning in Games","created":"2021-11-17","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":"2303.01673","title":"Near Optimal Memory-Regret Tradeoff for Online Learning","created":"2023-03-03","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":"2302.12370","title":"Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds","created":"2023-02-24","cited_by_count":14,"area":null},{"id":"2110.08627","title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2202.03334","title":"Policy Optimization for Stochastic Shortest Path","created":"2022-02-07","cited_by_count":13,"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":"2106.04700","title":"Scale Free Adversarial Multi Armed Bandits","created":"2021-06-08","cited_by_count":12,"area":null},{"id":"2111.05257","title":"Logarithmic Regret from Sublinear Hints","created":"2021-11-09","cited_by_count":12,"area":null},{"id":"2206.06810","title":"Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds","created":"2022-06-14","cited_by_count":12,"area":null},{"id":"2303.06825","title":"Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm","created":"2023-03-13","cited_by_count":12,"area":null},{"id":"2206.02344","title":"Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2206.14912","title":"Best of Both Worlds Model Selection","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2211.06358","title":"Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions","created":"2022-11-05","cited_by_count":11,"area":null},{"id":"2312.15433","title":"Best-of-Both-Worlds Algorithms for Linear Contextual Bandits","created":"2023-12-24","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":"2405.16118","title":"Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints","created":"2024-05-25","cited_by_count":10,"area":null},{"id":"2502.17625","title":"Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2202.07574","title":"Damped Online Newton Step for Portfolio Selection","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2410.12713","title":"How Does Variance Shape the Regret in Contextual Bandits?","created":"2024-10-16","cited_by_count":9,"area":null},{"id":"2501.14349","title":"Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound","created":"2025-01-24","cited_by_count":9,"area":null},{"id":"2110.14804","title":"Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers","created":"2021-10-27","cited_by_count":8,"area":null},{"id":"2206.09254","title":"Mutation-Driven Follow the Regularized Leader for Last-Iterate Convergence in Zero-Sum Games","created":"2022-06-18","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":"2410.03284","title":"uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs","created":"2024-10-04","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":"2405.10027","title":"The Real Price of Bandit Information in Multiclass Classification","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2410.07533","title":"Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2102.12722","title":"Combinatorial Bandits under Strategic Manipulations","created":"2021-02-25","cited_by_count":6,"area":null},{"id":"2109.05829","title":"Zeroth-order non-convex learning via hierarchical dual averaging","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2211.02703","title":"Online Learning and Bandits with Queried Hints","created":"2022-11-04","cited_by_count":6,"area":null},{"id":"2310.01609","title":"Adversarial Contextual Bandits Go Kernelized","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2403.04568","title":"Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition","created":"2024-03-07","cited_by_count":6,"area":"deeprl"},{"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":"2501.13358","title":"Learning to Bid in Non-Stationary Repeated First-Price Auctions","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2503.00419","title":"Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update","created":"2025-03-01","cited_by_count":5,"area":null},{"id":"2602.04761","title":"Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2107.09572","title":"Best-of-All-Worlds Bounds for Online Learning with Feedback Graphs","created":"2021-07-20","cited_by_count":4,"area":null},{"id":"2211.02233","title":"Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2402.10282","title":"Information Capacity Regret Bounds for Bandits with Mediator Feedback","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2403.03219","title":"LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits","created":"2024-03-05","cited_by_count":4,"area":null},{"id":"2412.07120","title":"Corrupted Learning Dynamics in Games","created":"2024-12-10","cited_by_count":4,"area":null},{"id":"2502.09257","title":"From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards","created":"2025-02-13","cited_by_count":4,"area":null},{"id":"2602.06348","title":"Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2605.09363","title":"Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions","created":"2026-05-10","cited_by_count":4,"area":"alignment"},{"id":"2208.09747","title":"Near-Optimal $\\Phi$-Regret Learning in Extensive-Form Games","created":"2022-08-20","cited_by_count":3,"area":null},{"id":"2310.01756","title":"Improved Algorithms for Adversarial Bandits with Unbounded Losses","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2402.08321","title":"Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring","created":"2024-02-13","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":"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":"2207.05437","title":"Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2304.14989","title":"Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2312.16489","title":"Best-of-Both-Worlds Linear Contextual Bandits","created":"2023-12-27","cited_by_count":2,"area":null},{"id":"2403.00930","title":"Scale-free Adversarial Reinforcement Learning","created":"2024-03-01","cited_by_count":2,"area":"deeprl"},{"id":"2502.15345","title":"Efficiently Solving Discounted MDPs with Predictions on Transition Matrices","created":"2025-02-21","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":"2506.13286","title":"The impact of uncertainty on regularized learning in games","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2510.11691","title":"Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2510.17103","title":"Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2511.02123","title":"Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2512.20368","title":"Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability","created":"2025-12-23","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":"2310.11188","title":"Adversarial Bandits with Multi-User Delayed Feedback: Theory and Application","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2405.02188","title":"Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes","created":"2024-05-03","cited_by_count":1,"area":null},{"id":"2408.08859","title":"Stochastic Bandits Robust to Adversarial Attacks","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2409.19092","title":"Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups","created":"2024-09-27","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":"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":"2510.22819","title":"Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2511.00637","title":"Stochastic Shortest Path with Sparse Adversarial Costs","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2602.07418","title":"Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2605.22191","title":"Bandit Convex Optimization with Gradient Prediction Adaptivity","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.29645","title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.06043","title":"Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2110.12544","title":"Online estimation and control with optimal pathlength regret","created":"2021-10-24","cited_by_count":0,"area":null}],"next_cursor":"100"}