{"total":29,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44,"area":null},{"id":"2307.08999","title":"Oracle Efficient Online Multicalibration and Omniprediction","created":"2023-07-18","cited_by_count":37,"area":null},{"id":"2202.08549","title":"Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries","created":"2022-02-17","cited_by_count":21,"area":null},{"id":"2305.00832","title":"First- and Second-Order Bounds for Adversarial Linear Contextual Bandits","created":"2023-05-01","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":"2205.13451","title":"Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback","created":"2022-05-26","cited_by_count":17,"area":null},{"id":"2311.06428","title":"A Trichotomy for Transductive Online Learning","created":"2023-11-10","cited_by_count":14,"area":null},{"id":"2102.09305","title":"Boosting for Online Convex Optimization","created":"2021-02-18","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":"2406.05287","title":"Group-wise oracle-efficient algorithms for online multi-group learning","created":"2024-06-07","cited_by_count":9,"area":null},{"id":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2310.04652","title":"Oracle Efficient Algorithms for Groupwise Regret","created":"2023-10-07","cited_by_count":8,"area":null},{"id":"2210.09385","title":"Adaptive Oracle-Efficient Online Learning","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2402.08576","title":"Regret Minimization in Stackelberg Games with Side Information","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2402.09483","title":"Oracle-Efficient Differentially Private Learning with Public Data","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2502.00204","title":"Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information","created":"2025-01-31","cited_by_count":6,"area":null},{"id":"2111.04688","title":"Universal and data-adaptive algorithms for model selection in linear contextual bandits","created":"2021-11-08","cited_by_count":5,"area":null},{"id":"2206.04475","title":"Individually Fair Learning with One-Sided Feedback","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2403.06812","title":"Monotone Individual Fairness","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2609.33760","title":"Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs","created":"2026-09-27","cited_by_count":3,"area":null},{"id":"2310.19025","title":"An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits","created":"2023-10-29","cited_by_count":2,"area":null},{"id":"2506.00135","title":"Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2509.15073","title":"Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2605.07155","title":"Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2107.03263","title":"Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2505.17365","title":"Improved and Oracle-Efficient Online $\\ell_1$-Multicalibration","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2610.17818","title":"Follow the Perturbed Leader for Linear Bandits: $\\sqrt{T}$ Regret over General Convex Sets","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}