Saved in:
Bibliographic Details
Main Authors: Lin, Ziyuan, Nguyen, Hoang Ngoc, Xu, Jie, Ruchkin, Ivan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.01039
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913082943471616
author Lin, Ziyuan
Nguyen, Hoang Ngoc
Xu, Jie
Ruchkin, Ivan
author_facet Lin, Ziyuan
Nguyen, Hoang Ngoc
Xu, Jie
Ruchkin, Ivan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01039
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Finite-Sample Analysis of Elimination in Active Hypothesis Testing
Lin, Ziyuan
Nguyen, Hoang Ngoc
Xu, Jie
Ruchkin, Ivan
Machine Learning
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.
title Finite-Sample Analysis of Elimination in Active Hypothesis Testing
topic Machine Learning
url https://arxiv.org/abs/2605.01039