arXiv Machine Learning June 5, 2026 By Ricardo J. Sandoval, Ian Waudby-Smith, Michael I. Jordan

Multi-Armed Sequential Hypothesis Testing by Betting

Read the original on arXiv Machine Learning →

arXiv:2603. 17925v2 Announce Type: replace-cross Abstract: We consider a variant of sequential testing by betting where, at each time step, the statistician is presented with multiple data sources (arms) and obtains data by choosing one of the arms.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 18

On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds

arXiv:2504. 19952v2 Announce Type: replace-cross Abstract: We present two general lower bounds for stopping times of sequential tests between arbitrary composite nulls $\mathcal P$ and alternatives $\mathcal Q$.

By Shubhada Agrawal, Ashwin Ram, Aaditya Ramdas

arXiv Statistics ML

2d ago

Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits

arXiv:2610.01951v1 Announce Type: cross Abstract: Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well u...

By Nam Nguyen, Tuan Quang Dam

arXiv Machine Learning

Aug 11

From Approachability Residuals to Anytime-Valid Evidence: The Online Convex Geometry of Testing by Betting

arXiv:2608. 09450v1 Announce Type: new Abstract: Betting-based sequential tests and Blackwell approachability are linked by a rate-explicit reduction through support-function residuals.

By Jinze Zhao

arXiv Machine Learning

Sep 24

Type-II Error Bounds for Test Supermartingales from Lower-Tail Hypotheses

arXiv:2609.27766v1 Announce Type: cross Abstract: In safe hypothesis testing with test supermartingals, Ville's inequality provides anytime-valid type-I error guarantees for every significance level...

By Patrick Forr\'e

arXiv Machine Learning

Jul 7

Replicability is Asymptotically Free in Multi-armed Bandits

arXiv:2402. 07391v3 Announce Type: replace-cross Abstract: We consider a replicable stochastic multi-armed bandit algorithm that ensures, with high probability, that the algorithm's sequence of actions is not affected by the randomness inherent in the dataset.

By Junpei Komiyama, Shinji Ito, Yuichi Yoshida, Souta Koshino

reinforcement-learning

arXiv Machine Learning

Aug 3

Parameter-Free Heavy-Tailed Bandits

arXiv:2607. 29460v1 Announce Type: new Abstract: Heavy-tailed distributions arise naturally in sequential decision-making problems such as financial investment, online advertising, and network management, where rare but extreme outcomes can dominate performance.

By Gianmarco Genalti, Alberto Maria Metelli

One email a morning, machine-written

Related stories

On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds

Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits

From Approachability Residuals to Anytime-Valid Evidence: The Online Convex Geometry of Testing by Betting

Type-II Error Bounds for Test Supermartingales from Lower-Tail Hypotheses

Replicability is Asymptotically Free in Multi-armed Bandits

Parameter-Free Heavy-Tailed Bandits