{"total":71,"rows":[{"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":"2402.09723","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","created":"2024-02-15","cited_by_count":37,"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":"2302.08893","title":"Active learning for data streams: a survey","created":"2023-02-17","cited_by_count":29,"area":null},{"id":"2106.04763","title":"Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2021-06-09","cited_by_count":22,"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":"2202.04294","title":"Optimal Clustering with Bandit Feedback","created":"2022-02-09","cited_by_count":15,"area":null},{"id":"2205.12086","title":"Information-Directed Selection for Top-Two Algorithms","created":"2022-05-24","cited_by_count":15,"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":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13,"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":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","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":"2106.14077","title":"The Role of Contextual Information in Best Arm Identification","created":"2021-06-26","cited_by_count":8,"area":null},{"id":"2110.13876","title":"Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2205.10936","title":"On Elimination Strategies for Bandit Fixed-Confidence Identification","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2211.12004","title":"Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning","created":"2022-11-22","cited_by_count":7,"area":null},{"id":"2311.05638","title":"Towards Instance-Optimality in Online PAC Reinforcement Learning","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2406.04137","title":"Optimal Batched Linear Bandits","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2202.06280","title":"On the complexity of All $\\varepsilon$-Best Arms Identification","created":"2022-02-13","cited_by_count":6,"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":"2411.01898","title":"Best-Arm Identification in Unimodal Bandits","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2502.02516","title":"Adaptive Exploration for Multi-Reward Multi-Policy Evaluation","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2412.02988","title":"Preference-based Pure Exploration","created":"2024-12-04","cited_by_count":5,"area":null},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","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":"2310.00539","title":"Thompson Exploration with Best Challenger Rule in Best Arm Identification","created":"2023-10-01","cited_by_count":4,"area":null},{"id":"2312.05880","title":"Data-driven optimal stopping: A pure exploration analysis","created":"2023-12-10","cited_by_count":4,"area":null},{"id":"2503.07824","title":"Pure Exploration with Feedback Graphs","created":"2025-03-10","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":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","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":"2305.06082","title":"Best Arm Identification in Bandits with Limited Precision Sampling","created":"2023-05-10","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":"2410.20640","title":"Near Optimal Pure Exploration in Logistic Bandits","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","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":"2311.00481","title":"Fixed-Budget Best-Arm Identification in Sparse Linear Bandits","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2501.11421","title":"Online Clustering of Data Sequences with Bandit Information","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2505.11985","title":"Variance-Optimal Arm Selection: Misallocation Minimization and Best Arm Identification","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2506.02386","title":"Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget","created":"2025-06-03","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":"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":"2607.06879","title":"Best-Arm Identification with Generative Proxy","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2201.02169","title":"Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach","created":"2022-01-06","cited_by_count":0,"area":null},{"id":"2302.09451","title":"Estimating Optimal Policy Value in General Linear Contextual Bandits","created":"2023-02-19","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":"2402.09467","title":"Optimal Thresholding Linear Bandit","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2502.01429","title":"An Algorithm for Fixed Budget Best Arm Identification with Combinatorial Exploration","created":"2025-02-03","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":"2506.22480","title":"Service Placement in Small Cell Networks Using Distributed Best Arm Identification in Linear Bandits","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2510.07862","title":"On the Optimality of Tracking Fisher Information in Adaptive Testing with Stochastic Binary Responses","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2601.09162","title":"Efficient Clustering in Stochastic Bandits","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.17430","title":"Active Hypothesis Testing for Correlated Combinatorial Anomaly Detection","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.05690","title":"Almost Asymptotically Optimal Active Clustering Through Pairwise Observations","created":"2026-02-05","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":"2609.13703","title":"Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.30360","title":"Cost-Aware Best-LLM Identification using Dueling Feedback","created":"2026-09-24","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}],"next_cursor":null}