{"total":48,"rows":[{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"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":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"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":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"id":"2202.10660","title":"Batched Dueling Bandits","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2502.17625","title":"Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback","created":"2025-02-24","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":"2111.03917","title":"Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits","created":"2021-11-06","cited_by_count":9,"area":null},{"id":"2210.14322","title":"ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits","created":"2022-10-25","cited_by_count":8,"area":null},{"id":"2210.02562","title":"Dueling Convex Optimization with General Preferences","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2405.03059","title":"Active Preference Learning for Ordering Items In- and Out-of-sample","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2107.02274","title":"Dueling Bandits with Adversarial Sleeping","created":"2021-07-05","cited_by_count":5,"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":"2204.04670","title":"Active Learning with Label Comparisons","created":"2022-04-10","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":"2407.18488","title":"Conversational Dueling Bandits in Generalized Linear Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2410.00362","title":"FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2307.11288","title":"Kernelized Offline Contextual Dueling Bandits","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2201.09798","title":"IMO$^3$: Interactive Multi-Objective Off-Policy Optimization","created":"2022-01-24","cited_by_count":3,"area":null},{"id":"2202.01879","title":"Learning from a Learning User for Optimal Recommendations","created":"2022-02-03","cited_by_count":3,"area":null},{"id":"2312.17229","title":"Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources","created":"2023-12-28","cited_by_count":3,"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":"2506.01250","title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2603.19221","title":"Online Learning and Equilibrium Computation with Ranking Feedback","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2608.15050","title":"Online Convex Optimization with Dueling Feedback","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2111.03447","title":"Contextual Bayesian optimization with binary outputs","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2403.15045","title":"DP-Dueling: Learning from Preference Feedback without Compromising User Privacy","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2406.12475","title":"Adversarial Multi-dueling Bandits","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2503.10215","title":"Adaptive Preference Aggregation","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2502.17077","title":"A comparative analysis of rank aggregation methods for the partial label ranking problem","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2503.07877","title":"Cost-Aware Optimal Pairwise Pure Exploration","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2506.21834","title":"PrefPaint: Enhancing Medical Image Inpainting through Expert Human Feedback","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2508.18841","title":"Recycling History: Efficient Recommendations from Contextual Dueling Bandits","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.00567","title":"Learning to Attack: A Bandit Approach to Adversarial Context Poisoning","created":"2026-02-28","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":"2605.01752","title":"Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions","created":"2026-05-03","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},{"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":"2609.28427","title":"Context-Continuous Preference Learning for Exoskeleton Personalization","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}