{"total":199,"rows":[{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2302.12022","title":"DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule","created":"2023-02-08","cited_by_count":85,"area":null},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2205.02160","title":"Making SGD Parameter-Free","created":"2022-05-04","cited_by_count":50,"area":null},{"id":"2110.14099","title":"Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio","created":"2021-10-27","cited_by_count":43,"area":null},{"id":"2110.06177","title":"Tracking the risk of a deployed model and detecting harmful distribution shifts","created":"2021-10-12","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":"2105.14363","title":"On the Theory of Reinforcement Learning with Once-per-Episode Feedback","created":"2021-05-29","cited_by_count":32,"area":null},{"id":"2203.03532","title":"E-detectors: a nonparametric framework for sequential change detection","created":"2022-03-07","cited_by_count":32,"area":null},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"area":null},{"id":"2302.08783","title":"SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance","created":"2023-02-17","cited_by_count":30,"area":null},{"id":"2103.06476","title":"Time-uniform central limit theory and asymptotic confidence sequences","created":"2021-03-11","cited_by_count":29,"area":null},{"id":"2210.14355","title":"Parameter-free Regret in High Probability with Heavy Tails","created":"2022-10-25","cited_by_count":28,"area":null},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"area":null},{"id":"2503.13050","title":"E-Values Expand the Scope of Conformal Prediction","created":"2025-03-17","cited_by_count":26,"area":null},{"id":"2302.03421","title":"A unified recipe for deriving (time-uniform) PAC-Bayes bounds","created":"2023-02-07","cited_by_count":25,"area":null},{"id":"2311.18274","title":"Semiparametric Efficient Inference in Adaptive Experiments","created":"2023-11-30","cited_by_count":23,"area":null},{"id":"2408.07511","title":"Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach","created":"2024-08-14","cited_by_count":23,"area":null},{"id":"2106.03243","title":"Neural Active Learning with Performance Guarantees","created":"2021-06-06","cited_by_count":22,"area":null},{"id":"2203.05481","title":"Fully Adaptive Composition in Differential Privacy","created":"2022-03-10","cited_by_count":22,"area":null},{"id":"2107.02266","title":"Near-optimal inference in adaptive linear regression","created":"2021-07-05","cited_by_count":21,"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":"2212.07383","title":"Sequential Kernelized Independence Testing","created":"2022-12-14","cited_by_count":16,"area":null},{"id":"2502.04294","title":"Prediction-Powered E-Values","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2102.09540","title":"Off-policy Confidence Sequences","created":"2021-02-18","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":"2201.07306","title":"Bregman Deviations of Generic Exponential Families","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2311.06412","title":"Online multiple testing with e-values","created":"2023-11-10","cited_by_count":12,"area":null},{"id":"2402.03126","title":"How Free is Parameter-Free Stochastic Optimization?","created":"2024-02-05","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":"2507.08721","title":"Monitoring Risks in Test-Time Adaptation","created":"2025-07-11","cited_by_count":11,"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":"2412.12910","title":"Sequential Harmful Shift Detection Without Labels","created":"2024-12-17","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":"2110.14243","title":"Online Selective Classification with Limited Feedback","created":"2021-10-27","cited_by_count":9,"area":null},{"id":"2212.14411","title":"Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations","created":"2022-12-29","cited_by_count":9,"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":"2402.06122","title":"Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams","created":"2024-02-09","cited_by_count":9,"area":null},{"id":"2409.16197","title":"Second Order Bounds for Contextual Bandits with Function Approximation","created":"2024-09-24","cited_by_count":9,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"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":"2205.08875","title":"Multi-disciplinary fairness considerations in machine learning for clinical trials","created":"2022-05-18","cited_by_count":8,"area":null},{"id":"2510.10232","title":"SGM: A Statistical Godel Machine for Risk-Controlled Recursive Self-Modification","created":"2025-10-11","cited_by_count":8,"area":null},{"id":"2606.15474","title":"Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines","created":"2026-06-13","cited_by_count":8,"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":"2203.04274","title":"Leveraging Initial Hints for Free in Stochastic Linear Bandits","created":"2022-03-08","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":"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":"2505.18000","title":"Anytime-valid, Bayes-assisted, Prediction-Powered Inference","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2605.30315","title":"Resolution Diagnostics for Paired LLM Evaluation","created":"2026-05-28","cited_by_count":7,"area":null},{"id":"2202.08728","title":"Nonparametric extensions of randomized response for private confidence sets","created":"2022-02-17","cited_by_count":6,"area":null},{"id":"2305.06884","title":"Risk-limiting Financial Audits via Weighted Sampling without Replacement","created":"2023-05-08","cited_by_count":6,"area":null},{"id":"2307.12897","title":"Anytime Model Selection in Linear Bandits","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2311.05931","title":"Early-Exit Neural Networks with Nested Prediction Sets","created":"2023-11-10","cited_by_count":6,"area":null},{"id":"2311.08168","title":"Time-Uniform Confidence Spheres for Means of Random Vectors","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2402.03915","title":"Learning Metrics that Maximise Power for Accelerated A/B-Tests","created":"2024-02-06","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":"2607.00871","title":"Self-Evolving Agents with Anytime-Valid Certificates","created":"2026-07-01","cited_by_count":6,"area":null},{"id":"2206.12441","title":"Joint Representation Training in Sequential Tasks with Shared Structure","created":"2022-06-24","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":"2307.01357","title":"Adaptive Principal Component Regression with Applications to Panel Data","created":"2023-07-03","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":"2410.15564","title":"Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2502.06096","title":"Post-detection inference for sequential changepoint localization","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2602.04364","title":"Anytime-Valid Conformal Risk Control","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2606.08517","title":"A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control","created":"2026-06-07","cited_by_count":5,"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":"2202.04166","title":"The Lifecycle of a Statistical Model: Model Failure Detection, Identification, and Refitting","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2204.13087","title":"Faster online calibration without randomization: interval forecasts and the power of two choices","created":"2022-04-27","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":"2412.08843","title":"Allocation Stability and Wald Inference under Variance-Aware UCB","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2508.01681","title":"Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2511.03606","title":"Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2512.13123","title":"Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences","created":"2025-12-15","cited_by_count":4,"area":null},{"id":"2606.29054","title":"When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation","created":"2026-06-27","cited_by_count":4,"area":null},{"id":"2607.17409","title":"Efficient Sequential Evaluation of Large Language Models","created":"2026-07-19","cited_by_count":4,"area":null},{"id":"2607.28520","title":"Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation","created":"2026-07-30","cited_by_count":4,"area":null},{"id":"2206.07234","title":"Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints","created":"2022-06-15","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":"2302.02544","title":"Sequential change detection via backward confidence sequences","created":"2023-02-06","cited_by_count":3,"area":null},{"id":"2304.01163","title":"The extended Ville's inequality for nonintegrable nonnegative supermartingales","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2306.10882","title":"AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents","created":"2023-06-19","cited_by_count":3,"area":null},{"id":"2402.09698","title":"Combining Evidence Across Filtrations","created":"2024-02-15","cited_by_count":3,"area":null},{"id":"2406.15648","title":"Testing the Feasibility of Linear Programs with Bandit Feedback","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2410.15057","title":"Asymptotic Time-Uniform Inference for Parameters in Averaged Stochastic Approximation","created":"2024-10-19","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":"2509.13130","title":"Fuzzy Prediction Sets: Conformal Prediction with E-values","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2509.26040","title":"Nonparametric inference under shape constraints: past, present and future","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2510.06478","title":"Anytime-Valid Answer Sufficiency Certificates for LLM Generation via Sequential Information Lift","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2602.02229","title":"Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2205.13689","title":"Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2208.03185","title":"Catoni-style Confidence Sequences under Infinite Variance","created":"2022-08-05","cited_by_count":2,"area":null},{"id":"2210.11133","title":"A lower confidence sequence for the changing mean of non-negative right heavy-tailed observations with bounded mean","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2302.14248","title":"Time-uniform confidence bands for the CDF under nonstationarity","created":"2023-02-28","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}],"next_cursor":"100"}