{"total":117,"rows":[{"id":"2107.01509","title":"Bayesian decision-making under misspecified priors with applications to meta-learning","created":"2021-07-03","cited_by_count":44,"area":null},{"id":"2206.05979","title":"Top Two Algorithms Revisited","created":"2022-06-13","cited_by_count":34,"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":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","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":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","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":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"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":"2205.12086","title":"Information-Directed Selection for Top-Two Algorithms","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2101.09855","title":"Weak Signal Asymptotics for Sequentially Randomized Experiments","created":"2021-01-25","cited_by_count":14,"area":null},{"id":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","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":"2110.12311","title":"Vector Optimization with Stochastic Bandit Feedback","created":"2021-10-23","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":"2210.05431","title":"Non-Asymptotic Analysis of a UCB-based Top Two Algorithm","created":"2022-10-11","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":"2311.05794","title":"An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed Bandits","created":"2023-11-09","cited_by_count":9,"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":"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":"2303.07154","title":"Differential Good Arm Identification","created":"2023-03-13","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":"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":"2112.06363","title":"Risk and optimal policies in bandit experiments","created":"2021-12-13","cited_by_count":7,"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":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2307.02108","title":"Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization","created":"2023-07-05","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":"2504.04204","title":"Adaptive Elicitation of Latent Information Using Natural Language","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2103.12198","title":"Challenges in Statistical Analysis of Data Collected by a Bandit Algorithm: An Empirical Exploration in Applications to Adaptively Randomized Experiments","created":"2021-03-22","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":"2310.18326","title":"Using Adaptive Bandit Experiments to Increase and Investigate Engagement in Mental Health","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2406.09574","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF","created":"2024-06-13","cited_by_count":6,"area":"alignment"},{"id":"2411.01898","title":"Best-Arm Identification in Unimodal Bandits","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2605.07042","title":"The Context Gathering Decision Process: A POMDP Framework for Agentic Search","created":"2026-05-07","cited_by_count":6,"area":"agents"},{"id":"2204.12620","title":"Rate-Constrained Remote Contextual Bandits","created":"2022-04-26","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":"2110.11181","title":"Sensing Cox Processes via Posterior Sampling and Positive Bases","created":"2021-10-21","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":"2206.09150","title":"Thompson Sampling for (Combinatorial) Pure Exploration","created":"2022-06-18","cited_by_count":4,"area":null},{"id":"2210.00340","title":"Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2305.09840","title":"Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planning","created":"2023-05-16","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":"2402.05878","title":"Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2024-02-08","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":"2110.00158","title":"Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2202.05182","title":"Remote Contextual Bandits","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2203.00820","title":"Partial Likelihood Thompson Sampling","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2206.06847","title":"On the Finite-Time Performance of the Knowledge Gradient Algorithm","created":"2022-06-14","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":"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":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","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":"2105.13420","title":"Model Selection for Production System via Automated Online Experiments","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2106.03221","title":"PAC Best Arm Identification Under a Deadline","created":"2021-06-06","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":"2301.12822","title":"Evaluating COVID-19 vaccine allocation policies using Bayesian $m$-top exploration","created":"2023-01-30","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":"2310.09597","title":"Adaptive maximization of social welfare","created":"2023-10-14","cited_by_count":2,"area":null},{"id":"2310.17901","title":"Improving the Knowledge Gradient Algorithm","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2401.03756","title":"Adaptive Experimental Design for Policy Learning","created":"2024-01-08","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":"2503.00273","title":"Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2109.15310","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","created":"2021-09-30","cited_by_count":1,"area":null},{"id":"2112.08507","title":"Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2202.05193","title":"Suboptimal Performance of the Bayes Optimal Algorithm in Frequentist Best Arm Identification","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2204.12043","title":"An Efficient Dynamic Sampling Policy For Monte Carlo Tree Search","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2208.05092","title":"Using Adaptive Experiments to Rapidly Help Students","created":"2022-08-10","cited_by_count":1,"area":null},{"id":"2305.14704","title":"Practical Batch Bayesian Sampling Algorithms for Online Adaptive Traffic Experimentation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2312.13875","title":"Best Arm Identification in Batched Multi-armed Bandit Problems","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2408.04869","title":"UCB Exploration for Fixed-Budget Bayesian Best Arm Identification","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2502.16659","title":"Optimizing Input Data Collection for Ranking and Selection","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2505.20583","title":"Balancing Performance and Costs in Best Arm Identification","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2505.22473","title":"Pure Exploration with Infinite Answers","created":"2025-05-28","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":"2506.03062","title":"Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.05329","title":"Admissibility of Completely Randomized Trials: A Large-Deviation Approach","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2507.08994","title":"Fixed-Confidence Multiple Change Point Identification under Bandit Feedback","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2509.15420","title":"Top-$k$ Feature Importance Ranking","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2509.19901","title":"Pure Exploration via Frank-Wolfe Self-Play","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2510.08794","title":"Deceptive Exploration in Multi-armed Bandits","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2601.22157","title":"Discovering Hidden Gems in Model Repositories","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2105.01390","title":"Optimal Algorithms for Range Searching over Multi-Armed Bandits","created":"2021-05-04","cited_by_count":0,"area":null},{"id":"2201.03065","title":"Selecting the Best Optimizing System","created":"2022-01-09","cited_by_count":0,"area":null},{"id":"2209.08197","title":"Thompson Sampling with Virtual Helping Agents","created":"2022-09-16","cited_by_count":0,"area":null},{"id":"2302.02033","title":"An Asymptotically Optimal Algorithm for the Convex Hull Membership Problem","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2303.07627","title":"Best arm identification in rare events","created":"2023-03-14","cited_by_count":0,"area":null},{"id":"2305.11908","title":"Sequential Best-Arm Identification with Application to Brain-Computer Interface","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2402.10429","title":"Fixed Confidence Best Arm Identification in the Bayesian Setting","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2402.15703","title":"Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2408.04531","title":"AExGym: Benchmarks and Environments for Adaptive Experimentation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2411.10695","title":"Series Expansion of Probability of Correct Selection for Improved Finite Budget Allocation in Ranking and Selection","created":"2024-11-16","cited_by_count":0,"area":null}],"next_cursor":"100"}