{"total":39,"rows":[{"id":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2109.13595","title":"The Fragility of Optimized Bandit Algorithms","created":"2021-09-28","cited_by_count":17,"area":null},{"id":"2102.12769","title":"No-Regret Reinforcement Learning with Heavy-Tailed Rewards","created":"2021-02-25","cited_by_count":14,"area":null},{"id":"2111.03290","title":"Maillard Sampling: Boltzmann Exploration Done Optimally","created":"2021-11-05","cited_by_count":13,"area":null},{"id":"2201.07306","title":"Bregman Deviations of Generic Exponential Families","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2105.09232","title":"Diffusion Approximations for Thompson Sampling in the Small Gap Regime","created":"2021-05-19","cited_by_count":12,"area":null},{"id":"2210.02087","title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2210.05660","title":"The Typical Behavior of Bandit Algorithms","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2206.03520","title":"Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2306.09048","title":"Optimal Best-Arm Identification in Bandits with Access to Offline Data","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2502.08870","title":"When and why randomised exploration works (in linear bandits)","created":"2025-02-13","cited_by_count":8,"area":null},{"id":"2505.23260","title":"Stable Thompson Sampling: Valid Inference via Variance Inflation","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2205.04901","title":"Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization","created":"2022-05-10","cited_by_count":6,"area":null},{"id":"2409.18909","title":"Best Arm Identification with Minimal Regret","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2604.13739","title":"Spectral Thompson sampling","created":"2026-04-15","cited_by_count":5,"area":null},{"id":"2109.04433","title":"Extreme Bandits using Robust Statistics","created":"2021-09-09","cited_by_count":4,"area":null},{"id":"2111.09724","title":"From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2303.06058","title":"A General Recipe for the Analysis of Randomized Multi-Armed Bandit Algorithms","created":"2023-03-10","cited_by_count":4,"area":null},{"id":"2310.00539","title":"Thompson Exploration with Best Challenger Rule in Best Arm Identification","created":"2023-10-01","cited_by_count":4,"area":null},{"id":"2110.00158","title":"Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2302.01544","title":"Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2309.10737","title":"Monte-Carlo tree search with uncertainty propagation via optimal transport","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2203.13151","title":"Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2304.03056","title":"Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms","created":"2023-04-06","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":"2501.19239","title":"Multi-agent Multi-armed Bandit with Fully Heavy-tailed Dynamics","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2312.15549","title":"Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs","created":"2023-12-24","cited_by_count":1,"area":null},{"id":"2402.15127","title":"Asymptotically and Minimax Optimal Regret Bounds for Multi-Armed Bandits with Abstention","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2410.02279","title":"On Lai's Upper Confidence Bound in Multi-Armed Bandits","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2501.03132","title":"Communication Bounds for the Distributed Experts Problem","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2502.14379","title":"Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2508.13749","title":"Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2510.05023","title":"Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2105.14114","title":"Asymptotically Optimal Bandits under Weighted Information","created":"2021-05-28","cited_by_count":0,"area":null},{"id":"2203.10214","title":"Thompson Sampling on Asymmetric $\\alpha$-Stable Bandits","created":"2022-03-19","cited_by_count":0,"area":null},{"id":"2309.06349","title":"Generalized Regret Analysis of Thompson Sampling using Fractional Posteriors","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2310.00642","title":"From Bandits Model to Deep Deterministic Policy Gradient, Reinforcement Learning with Contextual Information","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2310.12563","title":"Approximate information maximization for bandit games","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2610.18899","title":"Thompson Sampling for Learning in Zero-Sum Games","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}