{"total":63,"rows":[{"id":"2105.05806","title":"High-Dimensional Experimental Design and Kernel Bandits","created":"2021-05-12","cited_by_count":56,"area":null},{"id":"2105.13017","title":"Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits","created":"2021-05-27","cited_by_count":32,"area":null},{"id":"2104.03781","title":"Leveraging Good Representations in Linear Contextual Bandits","created":"2021-04-08","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":"2106.04763","title":"Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2021-06-09","cited_by_count":22,"area":null},{"id":"2101.08534","title":"Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback","created":"2021-01-21","cited_by_count":21,"area":null},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18,"area":null},{"id":"2111.01768","title":"Nearly Optimal Algorithms for Level Set Estimation","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2206.11183","title":"Active Learning with Safety Constraints","created":"2022-06-22","cited_by_count":16,"area":null},{"id":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2501.17513","title":"Sequential Learning of the Pareto Front for Multi-objective Bandits","created":"2025-01-29","cited_by_count":15,"area":null},{"id":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13,"area":null},{"id":"2110.12311","title":"Vector Optimization with Stochastic Bandit Feedback","created":"2021-10-23","cited_by_count":12,"area":null},{"id":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","cited_by_count":12,"area":null},{"id":"2103.10070","title":"Top-m identification for linear bandits","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2306.12774","title":"Pure Exploration in Bandits with Linear Constraints","created":"2023-06-22","cited_by_count":10,"area":null},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2205.10936","title":"On Elimination Strategies for Bandit Fixed-Confidence Identification","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2310.14129","title":"Optimal Batched Best Arm Identification","created":"2023-10-21","cited_by_count":8,"area":null},{"id":"2302.04441","title":"Multi-task Representation Learning for Pure Exploration in Linear Bandits","created":"2023-02-09","cited_by_count":6,"area":null},{"id":"2310.11015","title":"Pure Exploration in Asynchronous Federated Bandits","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2203.06297","title":"Instance-Dependent Regret Analysis of Kernelized Bandits","created":"2022-03-12","cited_by_count":5,"area":null},{"id":"2210.13083","title":"Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2109.05131","title":"Near Instance Optimal Model Selection for Pure Exploration Linear Bandits","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2309.08709","title":"Price of Safety in Linear Best Arm Identification","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2508.16487","title":"FraPPE: Fast and Efficient Preference-based Pure Exploration","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2207.11158","title":"SPRT-based Efficient Best Arm Identification in Stochastic Bandits","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2308.00978","title":"Certified Multi-Fidelity Zeroth-Order Optimization","created":"2023-08-02","cited_by_count":3,"area":null},{"id":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2409.05798","title":"Enhancing Preference-based Linear Bandits via Human Response Time","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2301.03785","title":"Best Arm Identification in Stochastic Bandits: Beyond $\\beta-$optimality","created":"2023-01-10","cited_by_count":2,"area":null},{"id":"2307.15154","title":"A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2401.17205","title":"Adaptive Experiment Design with Synthetic Controls","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2403.06230","title":"LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding Linear Bandit Problem","created":"2024-03-10","cited_by_count":2,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2410.20640","title":"Near Optimal Pure Exploration in Logistic Bandits","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2506.08127","title":"Constrained Pareto Set Identification with Bandit Feedback","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2507.04255","title":"Bandit Pareto Set Identification in a Multi-Output Linear Model","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2104.05294","title":"Pure Exploration with Structured Preference Feedback","created":"2021-04-12","cited_by_count":1,"area":"alignment"},{"id":"2206.04456","title":"Choosing Answers in $\\varepsilon$-Best-Answer Identification for Linear Bandits","created":"2022-06-09","cited_by_count":1,"area":null},{"id":"2308.15552","title":"Pure Exploration under Mediators' Feedback","created":"2023-08-29","cited_by_count":1,"area":"alignment"},{"id":"2407.02601","title":"Linear Submodular Maximization with Bandit Feedback","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2505.22473","title":"Pure Exploration with Infinite Answers","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.13390","title":"Experimental Design for Semiparametric Bandits","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2509.19901","title":"Pure Exploration via Frank-Wolfe Self-Play","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2605.05745","title":"Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.17515","title":"Anytime-valid Optimal Policy Identification","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2302.02033","title":"An Asymptotically Optimal Algorithm for the Convex Hull Membership Problem","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2305.19161","title":"Cooperative Thresholded Lasso for Sparse Linear Bandit","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2311.04731","title":"Robust Best-arm Identification in Linear Bandits","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2402.03737","title":"Differentially Private High Dimensional Bandits","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2402.09467","title":"Optimal Thresholding Linear Bandit","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2504.11866","title":"On the Problem of Best Arm Retention","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2510.04559","title":"Challenger-Based Combinatorial Bandits for Subcarrier Selection in OFDM Systems","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2603.10346","title":"On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.03969","title":"Nearly Optimal Best Arm Identification for Semiparametric Bandits","created":"2026-04-05","cited_by_count":0,"area":null},{"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":"2607.08979","title":"Optimal Top-$k$ Identification from Pairwise Comparisons","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.06670","title":"Data Efficient Sample Selection for In-Context Learning","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2610.16840","title":"Few-for-Many Best-Arm Identification in Multi-Objective Bandits","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18577","title":"When More Objectives Make Identification Easier: The Role of Preferences and Feedback","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}