{"total":91,"rows":[{"id":"2105.05806","title":"High-Dimensional Experimental Design and Kernel Bandits","created":"2021-05-12","cited_by_count":56,"area":null},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"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":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"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":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24,"area":"alignment"},{"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":"2106.01420","title":"Parallelizing Thompson Sampling","created":"2021-06-02","cited_by_count":20,"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":"2206.00121","title":"Near-Optimal Collaborative Learning in Bandits","created":"2022-05-31","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":"2210.15345","title":"PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits","created":"2022-10-25","cited_by_count":17,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","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":"2105.06499","title":"Improved Algorithms for Agnostic Pool-based Active Classification","created":"2021-05-13","cited_by_count":15,"area":null},{"id":"2202.05448","title":"Fast Rates in Pool-Based Batch Active Learning","created":"2022-02-11","cited_by_count":15,"area":null},{"id":"2106.11612","title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation","created":"2021-06-22","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":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","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":"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":"2205.01257","title":"Norm-Agnostic Linear Bandits","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","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":"2206.05255","title":"Interactively Learning Preference Constraints in Linear Bandits","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2306.07858","title":"Additive Causal Bandits with Unknown Graph","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2303.15256","title":"Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need","created":"2023-03-27","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":"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":"2506.12721","title":"Strategic Scaling of Test-Time Compute: A Bandit Learning Approach","created":"2025-06-15","cited_by_count":8,"area":"lr"},{"id":"2202.02407","title":"An Experimental Design Approach for Regret Minimization in Logistic Bandits","created":"2022-02-04","cited_by_count":7,"area":null},{"id":"2309.02898","title":"A Unified Framework for Discovering Discrete Symmetries","created":"2023-09-06","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":"2402.08406","title":"Transition Constrained Bayesian Optimization via Markov Decision Processes","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2410.08000","title":"AHA: Human-Assisted Out-of-Distribution Generalization and Detection","created":"2024-10-10","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":"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":"2406.10738","title":"Adaptive Experimentation When You Can't Experiment","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2311.00327","title":"Multi-task Representation Learning for Pure Exploration in Bilinear Bandits","created":"2023-11-01","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":"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":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","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":"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":"2308.10238","title":"Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2402.15441","title":"Active Few-Shot Fine-Tuning","created":"2024-02-13","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":"2507.04255","title":"Bandit Pareto Set Identification in a Multi-Output Linear Model","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2510.10730","title":"Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits","created":"2025-10-12","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":"2112.04083","title":"Best Arm Identification under Additive Transfer Bandits","created":"2021-12-08","cited_by_count":1,"area":null},{"id":"2311.00481","title":"Fixed-Budget Best-Arm Identification in Sparse Linear Bandits","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2402.13079","title":"Mode Estimation with Partial Feedback","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2412.13559","title":"Indirect Query Bayesian Optimization with Integrated Feedback","created":"2024-12-18","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":"2602.03972","title":"Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors","created":"2026-02-03","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":"2111.04915","title":"Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers","created":"2021-11-09","cited_by_count":0,"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":"2310.14751","title":"Efficient and Interpretable Bandit Algorithms","created":"2023-10-23","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":"2312.09674","title":"Optimal Regret Bounds for Collaborative Learning in Bandits","created":"2023-12-15","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":"2410.18844","title":"Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2501.17370","title":"Breaking the $\\log(1/\\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids","created":"2025-01-29","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":"2601.17430","title":"Active Hypothesis Testing for Correlated Combinatorial Anomaly Detection","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.01581","title":"Nearly Optimal Active Preference Learning and Its Application to LLM Alignment","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"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":"2604.21849","title":"Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions","created":"2026-04-23","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":"2607.14706","title":"MESHA: Mechanism-Enforced Sequential Halving for Strategic Linear Bandits","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.14319","title":"Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms","created":"2026-08-14","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":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","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":"2610.17760","title":"Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback","created":"2026-10-13","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}