mlsanityData to 14 Oct 2026

Game-theoretic statistics and safe anytime-valid inference

arXiv 2210.01948 ↗First posted 4 Oct 2022math.ST cs.GT cs.ITcited by 155

Not on the map. Why?

Abstract (arXiv)

Safe anytime-valid inference (SAVI) provides measures of statistical evidence and certainty -- e-processes for testing and confidence sequences for estimation -- that remain valid at all stopping times, accommodating continuous monitoring and analysis of accumulating data and optional stopping or continuation for any reason. These measures crucially rely on test martingales, which are nonnegative martingales starting at one. Since a test martingale is the wealth process of a player in a betting game, SAVI centrally employs game-theoretic intuition, language and mathematics. We summarize the SAVI goals and philosophy, and report recent advances in testing composite hypotheses and estimating functionals in nonparametric settings.

Key facts. Cited by 155 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Oct 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 17; 2024: 14; 2025: 27; 2026: 94.

155 papers.

Sort:

By area:

  1. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  2. 2022Anytime-valid off-policy inference for contextual banditscited by 37
  3. 2024A Unified Confidence Sequence for Generalized Linear Models, with Applications to Banditscited by 29
  4. 2023A unified recipe for deriving (time-uniform) PAC-Bayes boundscited by 25
  5. 2023Auditing Fairness by Bettingcited by 25
  6. 2023Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversioncited by 24
  7. 2023Semiparametric Efficient Inference in Adaptive Experimentscited by 23
  8. 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approachcited by 23
  9. 2025E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testingcited by 17
  10. 2025Prediction-Powered E-Valuescited by 16
  11. 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingalescited by 16
  12. 2024Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selectioncited by 15
38 more
  1. 2024Active, anytime-valid risk controlling prediction setscited by 14
  2. 2025Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stoppingcited by 14
  3. 2026PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agentscited by 13
  4. 2023Online multiple testing with e-valuescited by 12
  5. 2024Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Bettingcited by 11
  6. 2025Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guaranteescited by 11
  7. 2025Monitoring Risks in Test-Time Adaptationcited by 11
  8. 2022E-Valuating Classifier Two-Sample Testscited by 10
  9. 2023Likelihood Ratio Confidence Sets for Sequential Decision Makingcited by 10
  10. 2025On Continuous Monitoring of Risk Violations under Unknown Shiftcited by 10
  11. 2022Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observationscited by 9
  12. 2024Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streamscited by 9
  13. 2024An Auditing Test To Detect Behavioral Shift in Language Modelscited by 9
  14. 2023Huber-Robust Confidence Sequencescited by 7
  15. 2023Deep anytime-valid hypothesis testingcited by 7
  16. 2025Anytime-valid, Bayes-assisted, Prediction-Powered Inferencecited by 7
  17. 2026Detecting Multi-Agent Collusion Through Multi-Agent Interpretabilitycited by 7
  18. 2026Resolution Diagnostics for Paired LLM Evaluationcited by 7
  19. 2026ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Driftcited by 6
  20. 2026Self-Evolving Agents with Anytime-Valid Certificatescited by 6
  21. 2023Incentive-Theoretic Bayesian Inference for Collaborative Sciencecited by 5
  22. 2024Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Banditscited by 5
  23. 2025Post-detection inference for sequential changepoint localizationcited by 5
  24. 2025Generalization Bounds and Stopping Rules for Learning with Self-Selected Datacited by 5
  25. 2023Active Sequential Two-Sample Testingcited by 4
  26. 2025Optimistic Interior Point Methods for Sequential Hypothesis Testing by Bettingcited by 4
  27. 2025Vector-valued self-normalized concentration inequalities beyond sub-Gaussianitycited by 4
  28. 2025Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequencescited by 4
  29. 2026Testing For Distribution Shifts with Conditional Conformal Test Martingalescited by 4
  30. 2026The Stability of Online Algorithms in Performative Predictioncited by 4
  31. 2026When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generationcited by 4
  32. 2026Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretabilitycited by 4
  33. 2026Efficient Sequential Evaluation of Large Language Modelscited by 4
  34. 2023The extended Ville's inequality for nonintegrable nonnegative supermartingalescited by 3
  35. 2024Combining Evidence Across Filtrationscited by 3
  36. 2024Asymptotic Time-Uniform Inference for Parameters in Averaged Stochastic Approximationcited by 3
  37. 2025Toward Universal Laws of Outlier Propagationcited by 3
  38. 2025Simulation-Based Inference for Adaptive Experimentscited by 3

50 most cited of 155 All 155 (JSON)