Stacking machine learning classifiers to identify Higgs bosons at the LHC

Página do item simplificado
dc.citation.volume12
dc.contributor.authorAlves, A. [UNIFESP]
dc.coverageBristol
dc.date.accessioned2020-07-13T11:53:19Z
dc.date.available2020-07-13T11:53:19Z
dc.date.issued2017
dc.description.abstractMachine learning (ML) algorithms have been employed in the problem of classifying signal and background events with high accuracy in particle physics. In this paper, we compare the performance of a widespread ML technique, namely, stacked generalization, against the results of two state-of-art algorithms: (1) a deep neural network (DNN) in the task of discovering a new neutral Higgs boson and (2) a scalable machine learning system for tree boosting, in the Standard Model Higgs to tau leptons channel, both at the 8 TeV LHC. In a cut-and-count analysis, stacking three algorithms performed around 16% worse than DNN but demanding far less computation efforts, however, the same stacking outperforms boosted decision trees. Using the stacked classifiers in a multivariate statistical analysis (MVA), on the other hand, significantly enhances the statistical significance compared to cut-and-count in both Higgs processes, suggesting that combining an ensemble of simpler and faster ML algorithms with MVA tools is a better approach than building a complex state-of-art algorithm for cut-and-count.en
dc.description.affiliationUniv Fed Sao Paulo, Dept Fis, BR-09972270 Diadema, SP, Brazil
dc.description.affiliationUnifespUniv Fed Sao Paulo, Dept Fis, BR-09972270 Diadema, SP, Brazil
dc.description.sourceWeb of Science
dc.description.sponsorshipCNPq
dc.description.sponsorshipFAPESP
dc.description.sponsorshipIDCNPq: 307098/2014-1
dc.description.sponsorshipIDFAPESP: 2013/22079-8
dc.format.extent-
dc.identifierhttp://dx.doi.org/10.1088/1748-0221/12/05/T05005
dc.identifier.citationJournal Of Instrumentation. Bristol, v. 12, p. -, 2017.
dc.identifier.doi10.1088/1748-0221/12/05/T05005
dc.identifier.issn1748-0221
dc.identifier.urihttps://repositorio.unifesp.br/handle/11600/54535
dc.identifier.wosWOS:000405076600005
dc.language.isoeng
dc.publisherIop Publishing Ltd
dc.relation.ispartofJournal Of Instrumentation
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subjectAnalysis and statistical methodsen
dc.subjectPattern recognitionen
dc.subjectcluster findingen
dc.subjectcalibration and fitting methodsen
dc.titleStacking machine learning classifiers to identify Higgs bosons at the LHCen
dc.typeinfo:eu-repo/semantics/article
Arquivos
Coleções
ICAQF - Artigos