{"total":149,"rows":[{"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":"2206.05979","title":"Top Two Algorithms Revisited","created":"2022-06-13","cited_by_count":34,"area":null},{"id":"2111.12151","title":"Best Arm Identification with Safety Constraints","created":"2021-11-23","cited_by_count":25,"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":"2104.14527","title":"Online certification of preference-based fairness for personalized recommender systems","created":"2021-04-29","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":"2107.02266","title":"Near-optimal inference in adaptive linear regression","created":"2021-07-05","cited_by_count":21,"area":null},{"id":"2109.05700","title":"Exploiting Heterogeneity in Robust Federated Best-Arm Identification","created":"2021-09-13","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":"2206.00121","title":"Near-Optimal Collaborative Learning in Bandits","created":"2022-05-31","cited_by_count":18,"area":null},{"id":"2103.12452","title":"Bandits with many optimal arms","created":"2021-03-23","cited_by_count":17,"area":null},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","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":"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":"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":"2402.08672","title":"Model Assessment and Selection under Temporal Distribution Shift","created":"2024-02-13","cited_by_count":12,"area":null},{"id":"2506.05295","title":"Sample Complexity and Representation Ability of Test-time Scaling Paradigms","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"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":"2208.09215","title":"Almost Cost-Free Communication in Federated Best Arm Identification","created":"2022-08-19","cited_by_count":11,"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":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","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":"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":"2302.01223","title":"Practical Bandits: An Industry Perspective","created":"2023-02-02","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":"2412.03727","title":"Online Experimental Design With Estimation-Regret Trade-off Under Network Interference","created":"2024-12-04","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":"2109.04941","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2110.00115","title":"Comparing Sequential Forecasters","created":"2021-09-30","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":"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":"2403.12732","title":"Tighter Confidence Bounds for Sequential Kernel Regression","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2506.12721","title":"Strategic Scaling of Test-Time Compute: A Bandit Learning Approach","created":"2025-06-15","cited_by_count":8,"area":"lr"},{"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":"2301.09573","title":"Huber-Robust Confidence Sequences","created":"2023-01-23","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":"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":"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":"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":"2207.08015","title":"Parallel Best Arm Identification in Heterogeneous Environments","created":"2022-07-16","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":"2310.11015","title":"Pure Exploration in Asynchronous Federated Bandits","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2604.07796","title":"Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes","created":"2026-04-09","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":"2210.14369","title":"Adaptive Experimental Design and Counterfactual Inference","created":"2022-10-25","cited_by_count":5,"area":null},{"id":"2309.03145","title":"The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits","created":"2023-09-06","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":"2408.09598","title":"Anytime-Valid Inference for Double/Debiased Machine Learning of Causal Parameters","created":"2024-08-18","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":"2410.17835","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":"2109.04433","title":"Extreme Bandits using Robust Statistics","created":"2021-09-09","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":"2203.10124","title":"Approximate Function Evaluation via Multi-Armed Bandits","created":"2022-03-18","cited_by_count":4,"area":null},{"id":"2302.02570","title":"Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation","created":"2023-02-06","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":"2402.10870","title":"Best of Three Worlds: Adaptive Experimentation for Digital Marketing in Practice","created":"2024-02-16","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":"2604.05417","title":"Multi-Drafter Speculative Decoding with Alignment Feedback","created":"2026-04-07","cited_by_count":4,"area":"inference"},{"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":"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":"2212.07551","title":"Faster Maximum Inner Product Search in High Dimensions","created":"2022-12-14","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":"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":"2502.01425","title":"The Batch Complexity of Bandit Pure Exploration","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2502.08166","title":"From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2608.04333","title":"Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2106.03221","title":"PAC Best Arm Identification Under a Deadline","created":"2021-06-06","cited_by_count":2,"area":null},{"id":"2204.06664","title":"Achieving Representative Data via Convex Hull Feasibility Sampling Algorithms","created":"2022-04-13","cited_by_count":2,"area":null},{"id":"2208.05844","title":"Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions","created":"2022-08-11","cited_by_count":2,"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":"2303.11582","title":"Adaptive Experimentation at Scale: A Computational Framework for Flexible Batches","created":"2023-03-21","cited_by_count":2,"area":null},{"id":"2405.15090","title":"Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2411.01808","title":"Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2503.04855","title":"A characterization of sample adaptivity in UCB data","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.15643","title":"Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima","created":"2025-05-21","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":"2607.04824","title":"Probably Correct Optimal Stable Matching under Two-Sided Uncertainty","created":"2026-07-06","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":"2202.08180","title":"Geometry of the Minimum Volume Confidence Sets","created":"2022-02-16","cited_by_count":1,"area":null},{"id":"2210.01295","title":"Max-Quantile Grouped Infinite-Arm Bandits","created":"2022-10-04","cited_by_count":1,"area":null}],"next_cursor":"100"}