Mismatched binary hypothesis testing: error exponent sensitivity

We study the problem of mismatched binary hypothesis testing between i.i.d. distributions. We analyze the tradeoff between the pairwise error probability exponents when the actual distributions generating the observation are different from the distributions used in the likelihood ratio test, sequent...

Descripción completa

Detalles Bibliográficos
Autores: Boroumand, Parham, Guillén i Fábregas, A. (Albert)
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2022
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/55587
Acceso en línea:http://hdl.handle.net/10230/55587
http://dx.doi.org/10.1109/TIT.2022.3171438
Access Level:acceso abierto
Palabra clave:Hypothesis testing
Mismatch
Likelihood ratio test
Generalized likelihood ratio test
Sequenstial probability ratio test
id ES_b0342702e942eb4fc34e8aaad02e743f
oai_identifier_str oai:recercat.cat:10230/55587
network_acronym_str ES
network_name_str España
repository_id_str
spelling Mismatched binary hypothesis testing: error exponent sensitivityBoroumand, ParhamGuillén i Fábregas, A. (Albert)Hypothesis testingMismatchLikelihood ratio testGeneralized likelihood ratio testSequenstial probability ratio testWe study the problem of mismatched binary hypothesis testing between i.i.d. distributions. We analyze the tradeoff between the pairwise error probability exponents when the actual distributions generating the observation are different from the distributions used in the likelihood ratio test, sequential probability ratio test, and Hoeffding’s generalized likelihood ratio test in the composite setting. When the real distributions are within a small divergence ball of the test distributions, we find the deviation of the worst-case error exponent of each test with respect to the matched error exponent. In addition, we consider the case where an adversary tampers with the observation, again within a divergence ball of the observation type. We show that the tests are more sensitive to distribution mismatch than to adversarial observation tampering.This work was supported in part by the European Research Council under Grant 725411 and in part by the Spanish Ministry of Economy and Competitiveness under Grant PID2020-116683GB-C22.Institute of Electrical and Electronics Engineers (IEEE)202320232022info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/55587http://dx.doi.org/10.1109/TIT.2022.3171438reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésIEEE Transactions on Information Theory. 2022;68(10):6738-61.info:eu-repo/grantAgreement/EC/H2020/725411info:eu-repo/grantAgreement/ES/2PE/PID2020-116683GB-C22© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/TIT.2022.3171438info:eu-repo/semantics/openAccessoai:recercat.cat:10230/555872026-05-29T05:05:01Z
dc.title.none.fl_str_mv Mismatched binary hypothesis testing: error exponent sensitivity
title Mismatched binary hypothesis testing: error exponent sensitivity
spellingShingle Mismatched binary hypothesis testing: error exponent sensitivity
Boroumand, Parham
Hypothesis testing
Mismatch
Likelihood ratio test
Generalized likelihood ratio test
Sequenstial probability ratio test
title_short Mismatched binary hypothesis testing: error exponent sensitivity
title_full Mismatched binary hypothesis testing: error exponent sensitivity
title_fullStr Mismatched binary hypothesis testing: error exponent sensitivity
title_full_unstemmed Mismatched binary hypothesis testing: error exponent sensitivity
title_sort Mismatched binary hypothesis testing: error exponent sensitivity
dc.creator.none.fl_str_mv Boroumand, Parham
Guillén i Fábregas, A. (Albert)
author Boroumand, Parham
author_facet Boroumand, Parham
Guillén i Fábregas, A. (Albert)
author_role author
author2 Guillén i Fábregas, A. (Albert)
author2_role author
dc.subject.none.fl_str_mv Hypothesis testing
Mismatch
Likelihood ratio test
Generalized likelihood ratio test
Sequenstial probability ratio test
topic Hypothesis testing
Mismatch
Likelihood ratio test
Generalized likelihood ratio test
Sequenstial probability ratio test
description We study the problem of mismatched binary hypothesis testing between i.i.d. distributions. We analyze the tradeoff between the pairwise error probability exponents when the actual distributions generating the observation are different from the distributions used in the likelihood ratio test, sequential probability ratio test, and Hoeffding’s generalized likelihood ratio test in the composite setting. When the real distributions are within a small divergence ball of the test distributions, we find the deviation of the worst-case error exponent of each test with respect to the matched error exponent. In addition, we consider the case where an adversary tampers with the observation, again within a divergence ball of the observation type. We show that the tests are more sensitive to distribution mismatch than to adversarial observation tampering.
publishDate 2022
dc.date.none.fl_str_mv 2022
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/55587
http://dx.doi.org/10.1109/TIT.2022.3171438
url http://hdl.handle.net/10230/55587
http://dx.doi.org/10.1109/TIT.2022.3171438
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv IEEE Transactions on Information Theory. 2022;68(10):6738-61.
info:eu-repo/grantAgreement/EC/H2020/725411
info:eu-repo/grantAgreement/ES/2PE/PID2020-116683GB-C22
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416788047953920
score 15,812455

Similares en LA Referencia