Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models

Autores
Álvarez, E.; Spannowsky, M.; Szewc, Manuel
Año de publicación
2022
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The classification of jets induced by quarks or gluons is important for New Physics searches at high-energy colliders. However, available taggers usually rely on modeling the data through Monte Carlo simulations, which could veil intractable theoretical and systematical uncertainties. To significantly reduce biases, we propose an unsupervised learning algorithm that, given a sample of jets, can learn the SoftDrop Poissonian rates for quark- and gluon-initiated jets and their fractions. We extract the Maximum Likelihood Estimates for the mixture parameters and the posterior probability over them. We then construct a quark-gluon tagger and estimate its accuracy in actual data to be in the 0.65–0.7 range, below supervised algorithms but nevertheless competitive. We also show how relevant unsupervised metrics perform well, allowing for an unsupervised hyperparameter selection. Further, we find that this result is not affected by an angular smearing introduced to simulate detector effects for central jets. The presented unsupervised learning algorithm is simple; its result is interpretable and depends on very few assumptions.
Fil: Álvarez, E.. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina
Fil: Spannowsky, M.. University of Durham; Reino Unido
Fil: Szewc, Manuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina
Materia
INFERENCE
JETS
LHC
QCD
UNSUPERVISE LEARNING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/213499

id CONICETDig_55f8aaa29f4818b97d94a0ad4750b157
oai_identifier_str oai:ri.conicet.gov.ar:11336/213499
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture ModelsÁlvarez, E.Spannowsky, M.Szewc, ManuelINFERENCEJETSLHCQCDUNSUPERVISE LEARNINGhttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1The classification of jets induced by quarks or gluons is important for New Physics searches at high-energy colliders. However, available taggers usually rely on modeling the data through Monte Carlo simulations, which could veil intractable theoretical and systematical uncertainties. To significantly reduce biases, we propose an unsupervised learning algorithm that, given a sample of jets, can learn the SoftDrop Poissonian rates for quark- and gluon-initiated jets and their fractions. We extract the Maximum Likelihood Estimates for the mixture parameters and the posterior probability over them. We then construct a quark-gluon tagger and estimate its accuracy in actual data to be in the 0.65–0.7 range, below supervised algorithms but nevertheless competitive. We also show how relevant unsupervised metrics perform well, allowing for an unsupervised hyperparameter selection. Further, we find that this result is not affected by an angular smearing introduced to simulate detector effects for central jets. The presented unsupervised learning algorithm is simple; its result is interpretable and depends on very few assumptions.Fil: Álvarez, E.. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; ArgentinaFil: Spannowsky, M.. University of Durham; Reino UnidoFil: Szewc, Manuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; ArgentinaFrontiers Media2022-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/213499Álvarez, E.; Spannowsky, M.; Szewc, Manuel; Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models; Frontiers Media; Frontiers in Artificial Intelligence; 5; 3-2022; 1-122624-8212CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.frontiersin.org/articles/10.3389/frai.2022.852970/fullinfo:eu-repo/semantics/altIdentifier/doi/10.3389/frai.2022.852970info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:41:17Zoai:ri.conicet.gov.ar:11336/213499instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:41:17.527CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
title Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
spellingShingle Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
Álvarez, E.
INFERENCE
JETS
LHC
QCD
UNSUPERVISE LEARNING
title_short Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
title_full Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
title_fullStr Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
title_full_unstemmed Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
title_sort Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
dc.creator.none.fl_str_mv Álvarez, E.
Spannowsky, M.
Szewc, Manuel
author Álvarez, E.
author_facet Álvarez, E.
Spannowsky, M.
Szewc, Manuel
author_role author
author2 Spannowsky, M.
Szewc, Manuel
author2_role author
author
dc.subject.none.fl_str_mv INFERENCE
JETS
LHC
QCD
UNSUPERVISE LEARNING
topic INFERENCE
JETS
LHC
QCD
UNSUPERVISE LEARNING
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv The classification of jets induced by quarks or gluons is important for New Physics searches at high-energy colliders. However, available taggers usually rely on modeling the data through Monte Carlo simulations, which could veil intractable theoretical and systematical uncertainties. To significantly reduce biases, we propose an unsupervised learning algorithm that, given a sample of jets, can learn the SoftDrop Poissonian rates for quark- and gluon-initiated jets and their fractions. We extract the Maximum Likelihood Estimates for the mixture parameters and the posterior probability over them. We then construct a quark-gluon tagger and estimate its accuracy in actual data to be in the 0.65–0.7 range, below supervised algorithms but nevertheless competitive. We also show how relevant unsupervised metrics perform well, allowing for an unsupervised hyperparameter selection. Further, we find that this result is not affected by an angular smearing introduced to simulate detector effects for central jets. The presented unsupervised learning algorithm is simple; its result is interpretable and depends on very few assumptions.
Fil: Álvarez, E.. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina
Fil: Spannowsky, M.. University of Durham; Reino Unido
Fil: Szewc, Manuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina
description The classification of jets induced by quarks or gluons is important for New Physics searches at high-energy colliders. However, available taggers usually rely on modeling the data through Monte Carlo simulations, which could veil intractable theoretical and systematical uncertainties. To significantly reduce biases, we propose an unsupervised learning algorithm that, given a sample of jets, can learn the SoftDrop Poissonian rates for quark- and gluon-initiated jets and their fractions. We extract the Maximum Likelihood Estimates for the mixture parameters and the posterior probability over them. We then construct a quark-gluon tagger and estimate its accuracy in actual data to be in the 0.65–0.7 range, below supervised algorithms but nevertheless competitive. We also show how relevant unsupervised metrics perform well, allowing for an unsupervised hyperparameter selection. Further, we find that this result is not affected by an angular smearing introduced to simulate detector effects for central jets. The presented unsupervised learning algorithm is simple; its result is interpretable and depends on very few assumptions.
publishDate 2022
dc.date.none.fl_str_mv 2022-03
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/213499
Álvarez, E.; Spannowsky, M.; Szewc, Manuel; Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models; Frontiers Media; Frontiers in Artificial Intelligence; 5; 3-2022; 1-12
2624-8212
CONICET Digital
CONICET
url http://hdl.handle.net/11336/213499
identifier_str_mv Álvarez, E.; Spannowsky, M.; Szewc, Manuel; Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models; Frontiers Media; Frontiers in Artificial Intelligence; 5; 3-2022; 1-12
2624-8212
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.frontiersin.org/articles/10.3389/frai.2022.852970/full
info:eu-repo/semantics/altIdentifier/doi/10.3389/frai.2022.852970
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Frontiers Media
publisher.none.fl_str_mv Frontiers Media
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614443377360896
score 13.070432