Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at √s = 13TeV, corresponding to an integrated luminosity of 35.9 fb-1. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.
Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
Meridiani P.;Amapane N.;Argiro S.;Bellan R.;Bellora A.;Cappati A.;Costa M.;Covarelli R.;Kiani B.;Migliore E.;Monaco V.;Monteil E.;Obertino M. M.;Pacher L.;Angioni G. L. P.;Romero A.;Salvatico R.;Sola V.;Solano A.;Soldi D.;Shchelina K.;Rumerio P.;Ravera F.;
2020-01-01
Abstract
Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at √s = 13TeV, corresponding to an integrated luminosity of 35.9 fb-1. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.File | Dimensione | Formato | |
---|---|---|---|
Sirunyan_2020_J._Inst._15_P06005.pdf
Accesso aperto
Tipo di file:
PDF EDITORIALE
Dimensione
5.48 MB
Formato
Adobe PDF
|
5.48 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.