Robust Hypothesis Testing with Abstention

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Managoli, Malhar A., Sahasranand, K. R., Prabhakaran, Vinod M.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916579126542336
author Managoli, Malhar A.
Sahasranand, K. R.
Prabhakaran, Vinod M.
author_facet Managoli, Malhar A.
Sahasranand, K. R.
Prabhakaran, Vinod M.
contents We study the binary hypothesis testing problem where an adversary may potentially corrupt a fraction of the samples. The detector is, however, permitted to abstain from making a decision if (and only if) the adversary is present. We consider a few natural "contamination models" and characterize for them the trade-off between the error exponents of the four types of errors -- errors of deciding in favour of the incorrect hypothesis when the adversary is present and errors of abstaining or deciding in favour of the wrong hypothesis when the adversary is absent, under the two hypotheses.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12938
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Hypothesis Testing with Abstention
Managoli, Malhar A.
Sahasranand, K. R.
Prabhakaran, Vinod M.
Information Theory
We study the binary hypothesis testing problem where an adversary may potentially corrupt a fraction of the samples. The detector is, however, permitted to abstain from making a decision if (and only if) the adversary is present. We consider a few natural "contamination models" and characterize for them the trade-off between the error exponents of the four types of errors -- errors of deciding in favour of the incorrect hypothesis when the adversary is present and errors of abstaining or deciding in favour of the wrong hypothesis when the adversary is absent, under the two hypotheses.
title Robust Hypothesis Testing with Abstention
topic Information Theory
url https://arxiv.org/abs/2501.12938