Research

Paper

TESTING March 09, 2026

Weighted Chernoff information and optimal loss exponent in context-sensitive hypothesis testing

Authors

Mark Kelbert, El'mira Yu. Kalimulina

Abstract

We consider context-sensitive (binary) hypothesis testing for i.i.d. observations under a multiplicative weight function. We establish the logarithmic asymptotic, as the sample size grows, of the optimal total loss (sum of type-I and type-II losses) and express the corresponding error exponent through a weighted Chernoff information between the competing distributions. Our approach embeds weighted geometric mixtures into an exponential family and identifies the exponent as the maximizer of its log-normaliser. We also provide concentration bounds for a tilted weighted log-likelihood and derive explicit expressions for Gaussian and Poisson models, as well as further parametric examples.

Metadata

arXiv ID: 2603.08308
Provider: ARXIV
Primary Category: math.ST
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08308v1</id>\n    <title>Weighted Chernoff information and optimal loss exponent in context-sensitive hypothesis testing</title>\n    <updated>2026-03-09T12:31:03Z</updated>\n    <link href='https://arxiv.org/abs/2603.08308v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08308v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We consider context-sensitive (binary) hypothesis testing for i.i.d. observations under a multiplicative weight function. We establish the logarithmic asymptotic, as the sample size grows, of the optimal total loss (sum of type-I and type-II losses) and express the corresponding error exponent through a weighted Chernoff information between the competing distributions. Our approach embeds weighted geometric mixtures into an exponential family and identifies the exponent as the maximizer of its log-normaliser. We also provide concentration bounds for a tilted weighted log-likelihood and derive explicit expressions for Gaussian and Poisson models, as well as further parametric examples.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.ST'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IT'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.PR'/>\n    <published>2026-03-09T12:31:03Z</published>\n    <arxiv:comment>30 pages, no figures</arxiv:comment>\n    <arxiv:primary_category term='math.ST'/>\n    <author>\n      <name>Mark Kelbert</name>\n    </author>\n    <author>\n      <name>El'mira Yu. Kalimulina</name>\n    </author>\n  </entry>"
}