{"total":227,"rows":[{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"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":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29,"area":null},{"id":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25,"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":"2206.04646","title":"Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification","created":"2022-06-09","cited_by_count":20,"area":null},{"id":"2303.09468","title":"On the Existence of a Complexity in Fixed Budget Bandit Identification","created":"2023-03-16","cited_by_count":20,"area":null},{"id":"2206.00121","title":"Near-Optimal Collaborative Learning in Bandits","created":"2022-05-31","cited_by_count":18,"area":null},{"id":"2303.00950","title":"Open Problem: Optimal Best Arm Identification with Fixed Budget","created":"2023-03-02","cited_by_count":18,"area":null},{"id":"2110.15573","title":"A/B/n Testing with Control in the Presence of Subpopulations","created":"2021-10-29","cited_by_count":17,"area":null},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","cited_by_count":16,"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":"2307.00424","title":"Adaptive Algorithms for Relaxed Pareto Set Identification","created":"2023-07-01","cited_by_count":15,"area":null},{"id":"2407.06172","title":"On Speeding Up Language Model Evaluation","created":"2024-07-08","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":"2311.03992","title":"Bandit Pareto Set Identification: the Fixed Budget Setting","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2201.07306","title":"Bregman Deviations of Generic Exponential Families","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2210.00974","title":"Dealing with Unknown Variances in Best-Arm Identification","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2402.16710","title":"Cost Aware Best Arm Identification","created":"2024-02-26","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":"2312.12137","title":"Best Arm Identification with Fixed Budget: A Large Deviation Perspective","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2402.10592","title":"Optimizing Adaptive Experiments: A Unified Approach to Regret Minimization and Best-Arm Identification","created":"2024-02-16","cited_by_count":12,"area":null},{"id":"2403.03589","title":"Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choices","created":"2024-03-06","cited_by_count":12,"area":null},{"id":"2210.05431","title":"Non-Asymptotic Analysis of a UCB-based Top Two Algorithm","created":"2022-10-11","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":"2309.00591","title":"Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2601.21471","title":"Best Arm Identification with LLM Judges and Limited Human","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2302.01223","title":"Practical Bandits: An Industry Perspective","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2406.03033","title":"Optimal Multi-Fidelity Best-Arm Identification","created":"2024-06-05","cited_by_count":9,"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":"2109.04941","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","created":"2021-09-10","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":"2202.11474","title":"Residual Bootstrap Exploration for Stochastic Linear Bandit","created":"2022-02-23","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":"2210.00895","title":"On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits","created":"2022-09-30","cited_by_count":8,"area":null},{"id":"2210.07780","title":"Federated Best Arm Identification with Heterogeneous Clients","created":"2022-10-14","cited_by_count":8,"area":null},{"id":"2304.04091","title":"Best Arm Identification with Fairness Constraints on Subpopulations","created":"2023-04-08","cited_by_count":8,"area":null},{"id":"2306.09048","title":"Optimal Best-Arm Identification in Bandits with Access to Offline Data","created":"2023-06-15","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":"2102.07030","title":"Diffusion Approximations for a Class of Sequential Testing Problems","created":"2021-02-13","cited_by_count":7,"area":null},{"id":"2105.12978","title":"A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits","created":"2021-05-27","cited_by_count":7,"area":null},{"id":"2107.10492","title":"Bandit Quickest Changepoint Detection","created":"2021-07-22","cited_by_count":7,"area":null},{"id":"2110.12916","title":"On Slowly-varying Non-stationary Bandits","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2111.08862","title":"Max-Min Grouped Bandits","created":"2021-11-17","cited_by_count":7,"area":null},{"id":"2402.01400","title":"Query-Efficient Correlation Clustering with Noisy Oracle","created":"2024-02-02","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":"2409.05072","title":"A General Framework for Clustering and Distribution Matching with Bandit Feedback","created":"2024-09-08","cited_by_count":7,"area":null},{"id":"2111.07458","title":"Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination","created":"2021-11-14","cited_by_count":6,"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":"2302.07510","title":"Best Arm Identification for Stochastic Rising Bandits","created":"2023-02-15","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":"2308.12000","title":"On Universally Optimal Algorithms for A/B Testing","created":"2023-08-23","cited_by_count":6,"area":null},{"id":"2309.02202","title":"On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence","created":"2023-09-05","cited_by_count":6,"area":null},{"id":"2310.10359","title":"An Anytime Algorithm for Good Arm Identification","created":"2023-10-16","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":"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":"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":"2109.05047","title":"PAC Mode Estimation using PPR Martingale Confidence Sequences","created":"2021-09-10","cited_by_count":5,"area":null},{"id":"2202.04487","title":"Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget","created":"2022-02-09","cited_by_count":5,"area":null},{"id":"2204.05245","title":"Approximate Top-$m$ Arm Identification with Heterogeneous Reward Variances","created":"2022-04-11","cited_by_count":5,"area":null},{"id":"2211.15129","title":"On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2409.18909","title":"Best Arm Identification with Minimal Regret","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2410.15564","title":"Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2410.17835","title":"Optimal Streaming Algorithms for Multi-Armed Bandits","created":"2024-10-23","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":"2108.00230","title":"Pure Exploration and Regret Minimization in Matching Bandits","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2201.04469","title":"Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap","created":"2022-01-12","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":"2508.16487","title":"FraPPE: Fast and Efficient Preference-based Pure Exploration","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2512.13123","title":"Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences","created":"2025-12-15","cited_by_count":4,"area":null},{"id":"2605.02141","title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2110.03068","title":"Learning the Optimal Recommendation from Explorative Users","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2110.14628","title":"(Almost) Free Incentivized Exploration from Decentralized Learning Agents","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2203.15236","title":"Best Arm Identification in Restless Markov Multi-Armed Bandits","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2204.06910","title":"Measurement-based Admission Control in Sliced Networks: A Best Arm Identification Approach","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2205.13255","title":"Active Labeling: Streaming Stochastic Gradients","created":"2022-05-26","cited_by_count":3,"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":"2209.07330","title":"Best Arm Identification with Contextual Information under a Small Gap","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2210.12625","title":"Fast Beam Alignment via Pure Exploration in Multi-armed Bandits","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2301.08544","title":"Multi-Armed Bandits and Quantum Channel Oracles","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2302.02988","title":"Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds","created":"2023-02-06","cited_by_count":3,"area":null},{"id":"2310.13393","title":"Optimal Best Arm Identification with Fixed Confidence in Restless Bandits","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2310.19788","title":"Worst-Case Optimal Multi-Armed Gaussian Best Arm Identification with a Fixed Budget","created":"2023-10-30","cited_by_count":3,"area":null},{"id":"2312.12741","title":"Locally Optimal Fixed-Budget Best Arm Identification in Two-Armed Gaussian Bandits with Unknown Variances","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2402.19090","title":"Best Arm Identification with Resource Constraints","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2408.17313","title":"Fair Best Arm Identification with Fixed Confidence","created":"2024-08-30","cited_by_count":3,"area":null},{"id":"2502.01425","title":"The Batch Complexity of Bandit Pure Exploration","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2503.08896","title":"Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2509.21091","title":"Best-of-$\\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.23992","title":"Optimal Arm Elimination Algorithms for Combinatorial Bandits","created":"2025-10-28","cited_by_count":3,"area":null}],"next_cursor":"100"}