Sequential Adversarial Hypothesis Testing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Modak, Eeshan, Bakshi, Mayank, Dey, Bikash Kumar, Prabhakaran, Vinod M.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909900554108928
author Modak, Eeshan
Bakshi, Mayank
Dey, Bikash Kumar
Prabhakaran, Vinod M.
author_facet Modak, Eeshan
Bakshi, Mayank
Dey, Bikash Kumar
Prabhakaran, Vinod M.
contents We study the adversarial binary hypothesis testing problem in the sequential setting. Associated with each hypothesis is a closed, convex set of distributions. Given the hypothesis, each observation is generated according to a distribution chosen (from the set associated with the hypothesis) by an adversary who has access to past observations. In the sequential setting, the number of observations the detector uses to arrive at a decision is variable; this extra freedom improves the asymptotic performance of the test. We characterize the closure of the set of achievable pairs of error exponents. We also study the problem under constraints on the number of observations used and the probability of error incurred.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10181
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sequential Adversarial Hypothesis Testing
Modak, Eeshan
Bakshi, Mayank
Dey, Bikash Kumar
Prabhakaran, Vinod M.
Information Theory
We study the adversarial binary hypothesis testing problem in the sequential setting. Associated with each hypothesis is a closed, convex set of distributions. Given the hypothesis, each observation is generated according to a distribution chosen (from the set associated with the hypothesis) by an adversary who has access to past observations. In the sequential setting, the number of observations the detector uses to arrive at a decision is variable; this extra freedom improves the asymptotic performance of the test. We characterize the closure of the set of achievable pairs of error exponents. We also study the problem under constraints on the number of observations used and the probability of error incurred.
title Sequential Adversarial Hypothesis Testing
topic Information Theory
url https://arxiv.org/abs/2511.10181