Stacking machine learning classifiers to identify Higgs bosons at the LHC

Show simple item record

dc.contributor.author Alves, A. [UNIFESP]
dc.date.accessioned 2020-07-13T11:53:19Z
dc.date.available 2020-07-13T11:53:19Z
dc.date.issued 2017
dc.identifier http://dx.doi.org/10.1088/1748-0221/12/05/T05005
dc.identifier.citation Journal Of Instrumentation. Bristol, v. 12, p. -, 2017.
dc.identifier.issn 1748-0221
dc.identifier.uri https://repositorio.unifesp.br/handle/11600/54535
dc.description.abstract Machine 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.sponsorship CNPq
dc.description.sponsorship FAPESP
dc.format.extent -
dc.language.iso eng
dc.publisher Iop Publishing Ltd
dc.relation.ispartof Journal Of Instrumentation
dc.rights Acesso restrito
dc.subject Analysis and statistical methods en
dc.subject Pattern recognition en
dc.subject cluster finding en
dc.subject calibration and fitting methods en
dc.title Stacking machine learning classifiers to identify Higgs bosons at the LHC en
dc.type Artigo
dc.description.affiliation Univ Fed Sao Paulo, Dept Fis, BR-09972270 Diadema, SP, Brazil
dc.description.affiliationUnifesp Univ Fed Sao Paulo, Dept Fis, BR-09972270 Diadema, SP, Brazil
dc.description.sponsorshipID CNPq: 307098/2014-1
dc.description.sponsorshipID FAPESP: 2013/22079-8
dc.identifier.doi 10.1088/1748-0221/12/05/T05005
dc.description.source Web of Science
dc.identifier.wos WOS:000405076600005
dc.coverage Bristol
dc.citation.volume 12



File

File Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search


Browse

Statistics

My Account