{"total":95,"rows":[{"id":"2403.03208","title":"Active Statistical Inference","created":"2024-03-05","cited_by_count":50,"area":null},{"id":"2104.14074","title":"Statistical Inference with M-Estimators on Adaptively Collected Data","created":"2021-04-29","cited_by_count":40,"area":null},{"id":"2106.02029","title":"Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits","created":"2021-06-03","cited_by_count":40,"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":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36,"area":null},{"id":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32,"area":null},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"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":"2311.18274","title":"Semiparametric Efficient Inference in Adaptive Experiments","created":"2023-11-30","cited_by_count":23,"area":null},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2206.03944","title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","created":"2022-06-08","cited_by_count":22,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","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":"2412.06126","title":"UCB algorithms for multi-armed bandits: Precise regret and adaptive inference","created":"2024-12-09","cited_by_count":19,"area":null},{"id":"2101.09855","title":"Weak Signal Asymptotics for Sequentially Randomized Experiments","created":"2021-01-25","cited_by_count":14,"area":null},{"id":"2202.06891","title":"Counterfactual inference in sequential experiments","created":"2022-02-14","cited_by_count":13,"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":"2408.04595","title":"Inference with the Upper Confidence Bound Algorithm","created":"2024-08-08","cited_by_count":12,"area":null},{"id":"2109.08792","title":"Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making","created":"2021-09-18","cited_by_count":11,"area":null},{"id":"2106.01723","title":"Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning","created":"2021-06-03","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":"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":"2202.07079","title":"Synthetically Controlled Bandits","created":"2022-02-14","cited_by_count":8,"area":null},{"id":"2205.08875","title":"Multi-disciplinary fairness considerations in machine learning for clinical trials","created":"2022-05-18","cited_by_count":8,"area":null},{"id":"2212.14883","title":"Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent","created":"2022-12-30","cited_by_count":8,"area":null},{"id":"2409.15682","title":"Linear Contextual Bandits with Interference","created":"2024-09-24","cited_by_count":8,"area":"alignment"},{"id":"2505.23260","title":"Stable Thompson Sampling: Valid Inference via Variance Inflation","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2111.00137","title":"Efficient Inference Without Trading-off Regret in Bandits: An Allocation Probability Test for Thompson Sampling","created":"2021-10-30","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":"2303.02534","title":"Semi-parametric inference based on adaptively collected data","created":"2023-03-05","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":"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":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2304.05365","title":"Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2307.07320","title":"Adaptive Linear Estimating Equations","created":"2023-07-14","cited_by_count":6,"area":null},{"id":"2411.12036","title":"Prediction-Guided Active Experiments","created":"2024-11-18","cited_by_count":6,"area":null},{"id":"2307.01357","title":"Adaptive Principal Component Regression with Applications to Panel Data","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2110.15501","title":"Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning","created":"2021-10-29","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":"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":"2411.14341","title":"Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect","created":"2024-11-21","cited_by_count":4,"area":"deeprl"},{"id":"2412.08843","title":"Allocation Stability and Wald Inference under Variance-Aware UCB","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2507.11891","title":"Choosing the Better Bandit Algorithm under Data Sharing: When Do A/B Experiments Work?","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2509.14218","title":"Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2605.10405","title":"Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","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":"2310.00532","title":"Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference","created":"2023-10-01","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":"2402.17003","title":"Monitoring Fidelity of Online Reinforcement Learning Algorithms in Clinical Trials","created":"2024-02-26","cited_by_count":3,"area":"deeprl"},{"id":"2404.17398","title":"Online Policy Learning and Inference by Matrix Completion","created":"2024-04-26","cited_by_count":3,"area":null},{"id":"2411.12786","title":"Off-policy estimation with adaptively collected data: the power of online learning","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2506.02881","title":"Simulation-Based Inference for Adaptive Experiments","created":"2025-06-03","cited_by_count":3,"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":"2305.00403","title":"Optimal tests following sequential experiments","created":"2023-04-30","cited_by_count":2,"area":null},{"id":"2311.14359","title":"Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study","created":"2023-11-24","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":"2502.04673","title":"Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2502.16195","title":"Statistical Inference in Reinforcement Learning: A Selective Survey","created":"2025-02-22","cited_by_count":2,"area":"deeprl"},{"id":"2503.04855","title":"A characterization of sample adaptivity in UCB data","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2510.10245","title":"Kernel Treatment Effects with Adaptively Collected Data","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2512.20368","title":"Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability","created":"2025-12-23","cited_by_count":2,"area":null},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2607.08951","title":"A Statistical Test for the Benefits of Personalizing Interventions","created":"2026-07-09","cited_by_count":2,"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":"2305.14704","title":"Practical Batch Bayesian Sampling Algorithms for Online Adaptive Traffic Experimentation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2306.11839","title":"Should I Stop or Should I Go: Early Stopping with Heterogeneous Populations","created":"2023-06-20","cited_by_count":1,"area":null},{"id":"2309.12162","title":"Optimal Conditional Inference in Adaptive Experiments","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2401.12986","title":"Crowdsourced Adaptive Surveys","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2405.01281","title":"Demistifying Inference after Adaptive Experiments","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2405.19317","title":"Generalized Neyman Allocation for Locally Minimax Optimal Best-Arm Identification","created":"2024-05-29","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":"2510.07646","title":"Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2512.10156","title":"Inference for Batched Adaptive Experiments","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2602.21478","title":"Efficient Inference after Directionally Stable Adaptive Experiments","created":"2026-02-25","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":"2102.08975","title":"Adaptive Doubly Robust Estimator from Non-stationary Logging Policy under a Convergence of Average Probability","created":"2021-02-17","cited_by_count":0,"area":null},{"id":"2310.09545","title":"A Semiparametric Instrumented Difference-in-Differences Approach to Policy Learning","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2310.12324","title":"Opportunities for Adaptive Experiments to Enable Continuous Improvement in Computer Science Education","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2412.17753","title":"Minimax Optimal Simple Regret in Two-Armed Best-Arm Identification","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2501.19277","title":"On Pareto Optimality for Parametric Choice Bandits","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2509.00199","title":"Algorithm Adaptation Bias in Recommendation System Online Experiments","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2511.06639","title":"Bernstein-von Mises for Adaptively Collected Data","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2512.09850","title":"Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.04402","title":"Performative Learning Theory","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.15559","title":"Fixed-Horizon Self-Normalized Inference for Adaptive Experiments via Martingale AIPW/DML with Logged Propensities","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2605.31443","title":"Modeling Covariate Transition for Efficient Estimation of Longitudinal Treatment Effects in Randomized Experiments","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.00913","title":"Bandit Simulation for Average Reward Inference","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2608.12831","title":"Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing","created":"2026-08-13","cited_by_count":0,"area":"agents"},{"id":"2609.19709","title":"Odds-Ratio Thompson Sampling: A Specification and Design Guide for Contrast-Based Multi-Armed Bandits","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30273","title":"Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.39026","title":"Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}