{"total":41,"rows":[{"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":"2107.01264","title":"Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning","created":"2021-07-02","cited_by_count":34,"area":null},{"id":"2106.02553","title":"Fair Exploration via Axiomatic Bargaining","created":"2021-06-04","cited_by_count":22,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2206.00121","title":"Near-Optimal Collaborative Learning in Bandits","created":"2022-05-31","cited_by_count":18,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2312.12137","title":"Best Arm Identification with Fixed Budget: A Large Deviation Perspective","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2109.04941","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2110.13876","title":"Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2406.04137","title":"Optimal Batched Linear Bandits","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2109.01656","title":"Thompson Sampling for Bandits with Clustered Arms","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2110.12160","title":"Multi-armed Bandit Algorithm against Strategic Replication","created":"2021-10-23","cited_by_count":5,"area":null},{"id":"2102.05502","title":"On the Suboptimality of Thompson Sampling in High Dimensions","created":"2021-02-10","cited_by_count":4,"area":null},{"id":"2102.07254","title":"Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time","created":"2021-02-14","cited_by_count":4,"area":null},{"id":"2112.01452","title":"Indexed Minimum Empirical Divergence for Unimodal Bandits","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2301.13524","title":"Quantum contextual bandits and recommender systems for quantum data","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2506.15926","title":"Competing Bandits in Matching Markets via Super Stability","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2508.16487","title":"FraPPE: Fast and Efficient Preference-based Pure Exploration","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2405.17968","title":"Matroid Semi-Bandits in Sublinear Time","created":"2024-05-28","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":"2212.09429","title":"On the Complexity of Representation Learning in Contextual Linear Bandits","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2410.09597","title":"A Complete Characterization of Learnability for Stochastic Noisy Bandits","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.15643","title":"Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2102.02472","title":"Transfer Learning in Bandits with Latent Continuity","created":"2021-02-04","cited_by_count":1,"area":null},{"id":"2202.11735","title":"Truncated LinUCB for Stochastic Linear Bandits","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2212.06891","title":"Interactive Learning with Pricing for Optimal and Stable Allocations in Markets","created":"2022-12-13","cited_by_count":1,"area":null},{"id":"2410.05441","title":"Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2510.25811","title":"Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2101.06592","title":"TSEC: a framework for online experimentation under experimental constraints","created":"2021-01-17","cited_by_count":0,"area":null},{"id":"2207.04143","title":"Interactive Recommendations for Optimal Allocations in Markets with Constraints","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2305.19691","title":"Constant or logarithmic regret in asynchronous multiplayer bandits","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.01655","title":"MINTS: Minimalist Thompson Sampling","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.23414","title":"Leveraging Similarities in Multi-Armed Bandits","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.19963","title":"Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}