{"total":17,"rows":[{"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":"2402.16710","title":"Cost Aware Best Arm Identification","created":"2024-02-26","cited_by_count":13,"area":null},{"id":"2309.00591","title":"Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2306.02208","title":"Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits","created":"2023-06-03","cited_by_count":9,"area":null},{"id":"2202.09036","title":"Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation","created":"2022-02-18","cited_by_count":8,"area":null},{"id":"2210.14369","title":"Adaptive Experimental Design and Counterfactual Inference","created":"2022-10-25","cited_by_count":5,"area":null},{"id":"2306.00096","title":"Learning the Pareto Front Using Bootstrapped Observation Samples","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2409.18909","title":"Best Arm Identification with Minimal Regret","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2410.15564","title":"Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2402.10870","title":"Best of Three Worlds: Adaptive Experimentation for Digital Marketing in Practice","created":"2024-02-16","cited_by_count":4,"area":null},{"id":"2505.20583","title":"Balancing Performance and Costs in Best Arm Identification","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2510.19119","title":"Learning Peer Influence Probabilities with Linear Contextual Bandits","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2511.05802","title":"Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2511.22273","title":"UCB for Large-Scale Pure Exploration: Beyond Sub-Gaussianity","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2606.01799","title":"Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.14706","title":"MESHA: Mechanism-Enforced Sequential Halving for Strategic Linear Bandits","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.23432","title":"Experimentation and Commitment under Reward Shifts","created":"2026-07-26","cited_by_count":0,"area":null}],"next_cursor":null}