We propose a neural network training method capable of accounting for the effects of systematic variations of the data model in the training process and describe its extension towards neural network multiclass classification. The procedure is evaluated on the realistic case of the measurement of Higgs boson production via gluon fusion and vector boson fusion in the ττ decay channel at the CMS experiment. The neural network output functions are used to infer the signal strengths for inclusive production of Higgs bosons as well as for their production via gluon fusion and vector boson fusion. We observe improvements of 12 and 16% in the uncertainty in the signal strengths for gluon and vector-boson fusion, respectively, compared with a conventional neural network training based on cross-entropy.

Druzhkin, D., Borshch, V., Babaev, A., Uzunian, A., Slabospitskii, S., Kachanov, V., et al. (2025). Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC. THE EUROPEAN PHYSICAL JOURNAL. C, PARTICLES AND FIELDS, 85(11) [10.1140/epjc/s10052-025-14713-w].

Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC

Tabarelli de Fatis T.;Ragazzi S.;Pizzati G.;Pinolini B. S.;Perego A.;Palluotto S.;Paganoni M.;Moroni L.;Malberti M.;Lucchini M. T.;Lavizzari G.;Guzzi L.;Govoni P.;Ghezzi A.;Gerosa R.;Dinardo M. E.;De Guio F.;Cetorelli F.;Brivio F.;Xiao J.;
2025

Abstract

We propose a neural network training method capable of accounting for the effects of systematic variations of the data model in the training process and describe its extension towards neural network multiclass classification. The procedure is evaluated on the realistic case of the measurement of Higgs boson production via gluon fusion and vector boson fusion in the ττ decay channel at the CMS experiment. The neural network output functions are used to infer the signal strengths for inclusive production of Higgs bosons as well as for their production via gluon fusion and vector boson fusion. We observe improvements of 12 and 16% in the uncertainty in the signal strengths for gluon and vector-boson fusion, respectively, compared with a conventional neural network training based on cross-entropy.
Articolo in rivista - Articolo scientifico
Classification (of information); Learning systems; Neural networks; Uncertainty analysis
English
26-nov-2025
2025
85
11
1360
open
Druzhkin, D., Borshch, V., Babaev, A., Uzunian, A., Slabospitskii, S., Kachanov, V., et al. (2025). Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC. THE EUROPEAN PHYSICAL JOURNAL. C, PARTICLES AND FIELDS, 85(11) [10.1140/epjc/s10052-025-14713-w].
File in questo prodotto:
File Dimensione Formato  
unpaywall-bitstream--133656738.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 2.85 MB
Formato Adobe PDF
2.85 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/593903
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
Social impact