{"total":57,"rows":[{"id":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","cited_by_count":62,"area":"alignment"},{"id":"2101.12745","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","created":"2021-01-29","cited_by_count":45,"area":null},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41,"area":null},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"area":null},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2310.18554","title":"Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion","created":"2023-10-28","cited_by_count":24,"area":null},{"id":"2404.06831","title":"Generalized Linear Bandits with Limited Adaptivity","created":"2024-04-10","cited_by_count":22,"area":null},{"id":"2110.10018","title":"Dynamic pricing and assortment under a contextual MNL demand","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2405.09831","title":"Nearly Minimax Optimal Regret for Multinomial Logistic Bandit","created":"2024-05-16","cited_by_count":20,"area":null},{"id":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2507.11847","title":"Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update","created":"2025-07-16","cited_by_count":16,"area":null},{"id":"2502.10020","title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","created":"2025-02-14","cited_by_count":15,"area":null},{"id":"2103.05750","title":"Regret Bounds for Generalized Linear Bandits under Parameter Drift","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2311.07565","title":"Exploration via linearly perturbed loss minimisation","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2103.11489","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","created":"2021-03-21","cited_by_count":12,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2405.17061","title":"Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation","created":"2024-05-27","cited_by_count":10,"area":"deeprl"},{"id":"2404.10776","title":"Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback","created":"2024-04-16","cited_by_count":9,"area":"alignment"},{"id":"2402.12042","title":"Linear bandits with polylogarithmic minimax regret","created":"2024-02-19","cited_by_count":8,"area":null},{"id":"2403.05385","title":"Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning","created":"2024-03-08","cited_by_count":8,"area":"offlinerl"},{"id":"2410.01112","title":"Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2202.02407","title":"An Experimental Design Approach for Regret Minimization in Logistic Bandits","created":"2022-02-04","cited_by_count":7,"area":null},{"id":"2405.20165","title":"Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2024-05-30","cited_by_count":7,"area":"deeprl"},{"id":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2601.01069","title":"Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs","created":"2026-01-03","cited_by_count":5,"area":null},{"id":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2508.01681","title":"Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2601.19300","title":"Queue Length Regret Bounds for Contextual Queueing Bandits","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2109.14412","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2507.05306","title":"Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2601.09825","title":"Eluder dimension: localise it!","created":"2026-01-14","cited_by_count":3,"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":"2504.02324","title":"Dynamic Assortment Selection and Pricing with Censored Preference Feedback","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.13163","title":"Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2508.03072","title":"Achieving Limited Adaptivity for Multinomial Logistic Bandits","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.18713","title":"Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options","created":"2025-10-21","cited_by_count":2,"area":"alignment"},{"id":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2405.11226","title":"The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedback","created":"2024-05-18","cited_by_count":1,"area":"alignment"},{"id":"2505.22820","title":"Preference Learning with Response Time: Robust Losses and Guarantees","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2602.00417","title":"Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.10971","title":"A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.22161","title":"Logistic Bandits with $\\tilde{O}(\\sqrt{dT})$ Regret without Context Diversity Assumptions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.09454","title":"Optimal Regret for Single Index Bandits","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2303.02691","title":"Revisiting Weighted Strategy for Non-stationary Parametric Bandits","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2305.18333","title":"Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics","created":"2023-05-24","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":"2509.04194","title":"Stochastic Matching Bandits with Rare Optimization Updates","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.17390","title":"Exploration via Feature Perturbation in Contextual Bandits","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2605.19768","title":"Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2605.23650","title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2605.25592","title":"Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.11968","title":"Efficient Multinomial Logistic Bandit via Frequent Directions","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.12919","title":"Beyond Second-Order Information: Paid Logistic Regression with Noisy Features","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}