{"total":23,"rows":[{"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":"2404.06013","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","created":"2024-04-09","cited_by_count":27,"area":null},{"id":"2310.00968","title":"Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits","created":"2023-10-02","cited_by_count":22,"area":null},{"id":"2303.08816","title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2202.10660","title":"Batched Dueling Bandits","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9,"area":null},{"id":"2210.02562","title":"Dueling Convex Optimization with General Preferences","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2306.02628","title":"Active Ranking of Experts Based on their Performances in Many Tasks","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2202.06694","title":"Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences","created":"2022-02-14","cited_by_count":5,"area":null},{"id":"2302.06595","title":"When Can We Track Significant Preference Shifts in Dueling Bandits?","created":"2023-02-13","cited_by_count":5,"area":null},{"id":"2408.14603","title":"Biased Dueling Bandits with Stochastic Delayed Feedback","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2209.12108","title":"An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem","created":"2022-09-25","cited_by_count":2,"area":null},{"id":"2403.12950","title":"Non-Stationary Dueling Bandits Under a Weighted Borda Criterion","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2405.16168","title":"Multi-Player Approaches for Dueling Bandits","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2503.11209","title":"Clustering Items through Bandit Feedback: Finding the Right Feature out of Many","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2406.12475","title":"Adversarial Multi-dueling Bandits","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2410.23867","title":"QuACK: A Multipurpose Queuing Algorithm for Cooperative $k$-Armed Bandits","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2101.10670","title":"Ordinal Monte Carlo Tree Search","created":"2021-01-26","cited_by_count":0,"area":null},{"id":"2111.00870","title":"Statistical Consequences of Dueling Bandits","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2603.01171","title":"PARWiS: Winner determination under shoestring budgets using active pairwise comparisons","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.18972","title":"Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.25025","title":"A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.00846","title":"CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM","created":"2026-05-30","cited_by_count":0,"area":null}],"next_cursor":null}