English

Finite-Sample Analysis of Elimination in Active Hypothesis Testing

Machine Learning 2026-05-05 v1

Abstract

A fixed-confidence, finite-sample problem of active hypothesis testing arises in many safety-critical applications. Situated in the context of sequential hypothesis testing, this paper studies the effect of hypothesis elimination on the stopping time. We introduce an elimination-augmented Track-and-Stop algorithm, in which champion-specific active-opponent sets are progressively pruned, and sensing effort is reallocated toward the surviving alternatives. Our analysis derives a non-asymptotic upper bound on the expected stopping time. The gain in finite-sample from elimination appears on the scale of the non-leading term, resulting from tighter tracking and concentration constants on the reduced hypothesis set. Furthermore, we introduce an aggressiveness parameter to modulate the trade-off between faster elimination and weaker confidence guarantee. An experimental study on synthetic Gaussian instances confirms the theoretical predictions.

Keywords

Cite

@article{arxiv.2605.01039,
  title  = {Finite-Sample Analysis of Elimination in Active Hypothesis Testing},
  author = {Ziyuan Lin and Hoang Ngoc Nguyen and Jie Xu and Ivan Ruchkin},
  journal= {arXiv preprint arXiv:2605.01039},
  year   = {2026}
}

Comments

Submitted to IEEE Conference on Decision and Control (CDC) 2026. 18 pages, 4 figures

R2 v1 2026-07-01T12:45:52.721Z