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.

Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC / Null, N., Chekhovsky, V., Hayrapetyan, A., Makarenko, V., Tumasyan, A., Adam, W., Andrejkovic, J.W., Benato, L., Bergauer, T., Chatterjee, S., Damanakis, K., Dragicevic, M., Hussain, P.S., Jeitler, M., Krammer, N., Li, A., Liko, D., Mikulec, I., Schieck, J., Schöfbeck, R., et al.. - In: EUROPEAN PHYSICAL JOURNAL. C, PARTICLES AND FIELDS. - ISSN 1434-6052. - 85:11(2025 Nov), pp. 1-37. [10.1140/epjc/s10052-025-14713-w]

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

Cunqueiro Mendez, L.;Del Re, D.;Organtini, G.;Paramatti, R.;Rahatlou, S.;Santanastasio, F.;
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.
2025-11
CMS; machine learning; systematic uncertainties
01 Pubblicazione su rivista::01a Articolo in rivista
Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC / Null, N., Chekhovsky, V., Hayrapetyan, A., Makarenko, V., Tumasyan, A., Adam, W., Andrejkovic, J.W., Benato, L., Bergauer, T., Chatterjee, S., Damanakis, K., Dragicevic, M., Hussain, P.S., Jeitler, M., Krammer, N., Li, A., Liko, D., Mikulec, I., Schieck, J., Schöfbeck, R., et al.. - In: EUROPEAN PHYSICAL JOURNAL. C, PARTICLES AND FIELDS. - ISSN 1434-6052. - 85:11(2025 Nov), pp. 1-37. [10.1140/epjc/s10052-025-14713-w]
File allegati a questo prodotto
File Dimensione Formato  
Chekhovsky_Development-of-systematic_2025.pdf

accesso aperto

Note: Articolo su rivista
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 2.85 MB
Formato Adobe PDF
2.85 MB Adobe PDF

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/11573/1779712
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact