{"total":23,"rows":[{"id":"2202.06151","title":"Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits","created":"2022-02-12","cited_by_count":22,"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":"2106.04700","title":"Scale Free Adversarial Multi Armed Bandits","created":"2021-06-08","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":"2405.10027","title":"The Real Price of Bandit Information in Multiclass Classification","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2103.05907","title":"Linear Bandits on Uniformly Convex Sets","created":"2021-03-10","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":"2205.13114","title":"Contextual Pandora's Box","created":"2022-05-26","cited_by_count":5,"area":null},{"id":"2102.05134","title":"Local and Global Uniform Convexity Conditions","created":"2021-02-09","cited_by_count":4,"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":"2608.04149","title":"Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization","created":"2026-08-04","cited_by_count":4,"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":"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":"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":"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":"2506.19752","title":"On the necessity of adaptive regularisation:Optimal anytime online learning on $\\boldsymbol{\\ell_p}$-balls","created":"2025-06-24","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":"2604.13738","title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.10299","title":"Nearly-Optimal Algorithm for Adversarial Kernelized Bandits","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2506.01685","title":"Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2508.05844","title":"Online Budget Allocation with Censored Semi-Bandit Feedback","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2601.23164","title":"Stochastic Linear Bandits with Parameter Noise","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2608.15996","title":"Toward Optimal Second-Order Path-Length Guarantee for Adversarial Multi-Armed Bandits","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}