{"total":286,"rows":[{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2210.10768","title":"Anytime-valid off-policy inference for contextual bandits","created":"2022-10-19","cited_by_count":37,"area":null},{"id":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37,"area":"mllm"},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2106.02126","title":"A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms","created":"2021-06-03","cited_by_count":30,"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":"2111.12151","title":"Best Arm Identification with Safety Constraints","created":"2021-11-23","cited_by_count":25,"area":null},{"id":"2106.02900","title":"Differentially Private Multi-Armed Bandits in the Shuffle Model","created":"2021-06-05","cited_by_count":24,"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":"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":"2103.09267","title":"Martingale Methods for Sequential Estimation of Convex Functionals and Divergences","created":"2021-03-16","cited_by_count":18,"area":null},{"id":"2105.04273","title":"Loss-Aversively Fair Classification","created":"2021-05-10","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":"2109.13595","title":"The Fragility of Optimized Bandit Algorithms","created":"2021-09-28","cited_by_count":17,"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":"2111.01768","title":"Nearly Optimal Algorithms for Level Set Estimation","created":"2021-11-02","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":"2302.04375","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","created":"2023-02-08","cited_by_count":17,"area":null},{"id":"2306.12214","title":"More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity","created":"2023-06-21","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":"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":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2106.13013","title":"A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2109.08229","title":"Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling","created":"2021-09-16","cited_by_count":15,"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":"2401.02749","title":"Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding","created":"2024-01-05","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":"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":"2110.08627","title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","cited_by_count":13,"area":null},{"id":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","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":"2106.04193","title":"Targeted Active Learning for Bayesian Decision-Making","created":"2021-06-08","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":"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":"2111.09885","title":"Rate-optimal Bayesian Simple Regret in Best Arm Identification","created":"2021-11-18","cited_by_count":11,"area":null},{"id":"2202.11795","title":"Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2206.05255","title":"Interactively Learning Preference Constraints in Linear Bandits","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2208.09215","title":"Almost Cost-Free Communication in Federated Best Arm Identification","created":"2022-08-19","cited_by_count":11,"area":null},{"id":"2202.12888","title":"Meta-Learning for Simple Regret Minimization","created":"2022-02-25","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":"2310.01547","title":"On the near-optimality of betting confidence sets for bounded means","created":"2023-10-02","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":"2102.07711","title":"Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification","created":"2021-02-15","cited_by_count":9,"area":"safety"},{"id":"2106.10417","title":"Variance-Dependent Best Arm Identification","created":"2021-06-19","cited_by_count":9,"area":null},{"id":"2206.07883","title":"Combinatorial Pure Exploration of Causal Bandits","created":"2022-06-16","cited_by_count":9,"area":null},{"id":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2211.14768","title":"Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2306.02208","title":"Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits","created":"2023-06-03","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":"2106.14866","title":"Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits","created":"2021-06-28","cited_by_count":8,"area":null},{"id":"2107.07322","title":"A unified framework for bandit multiple testing","created":"2021-07-15","cited_by_count":8,"area":null},{"id":"2202.09036","title":"Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation","created":"2022-02-18","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":"2311.09068","title":"Learning Fair Division from Bandit Feedback","created":"2023-11-15","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":"2111.08862","title":"Max-Min Grouped Bandits","created":"2021-11-17","cited_by_count":7,"area":null},{"id":"2303.02534","title":"Semi-parametric inference based on adaptively collected data","created":"2023-03-05","cited_by_count":7,"area":null},{"id":"2303.10565","title":"Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games","created":"2023-03-19","cited_by_count":7,"area":null},{"id":"2310.16252","title":"Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2310.18465","title":"Nearly Minimax Optimal Submodular Maximization with Bandit Feedback","created":"2023-10-27","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":"2402.01400","title":"Query-Efficient Correlation Clustering with Noisy Oracle","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2404.16954","title":"Taming False Positives in Out-of-Distribution Detection with Human Feedback","created":"2024-04-25","cited_by_count":7,"area":null},{"id":"2406.11485","title":"Active clustering with bandit feedback","created":"2024-06-17","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":"2504.19952","title":"On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds","created":"2025-04-28","cited_by_count":7,"area":null},{"id":"2110.14864","title":"Selective Sampling for Online Best-arm Identification","created":"2021-10-28","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":"2306.07549","title":"Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances","created":"2023-06-13","cited_by_count":6,"area":null},{"id":"2306.07761","title":"Multi-Fidelity Multi-Armed Bandits Revisited","created":"2023-06-13","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":"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":"2509.15929","title":"Improving Monte Carlo Tree Search for Symbolic Regression","created":"2025-09-19","cited_by_count":6,"area":null},{"id":"2108.01152","title":"Maximizing and Satisficing in Multi-armed Bandits with Graph Information","created":"2021-08-02","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":"2210.14369","title":"Adaptive Experimental Design and Counterfactual Inference","created":"2022-10-25","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":"2401.15879","title":"lil'HDoC: An Algorithm for Good Arm Identification under Small Threshold Gap","created":"2024-01-29","cited_by_count":5,"area":null},{"id":"2405.11548","title":"Adaptive Online Experimental Design for Causal Discovery","created":"2024-05-19","cited_by_count":5,"area":null},{"id":"2406.02282","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","created":"2024-06-04","cited_by_count":5,"area":"deeprl"}],"next_cursor":"100"}