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

(CMS Collaboration) Chekhovsky, Vladimir ; ... ; Giljanović, Duje ; Godinović, Nikola ; Lelas, Damir ; Šćulac, Ana ; Kovač, Marko ; Petković, Andro ; Šćulac, Toni ; Bargassa, Pedrame ; Brigljević, Vuko ; Chitroda, Bhakti Kanulal ; Ferenček, Dinko ; Jakovčić, Krešimir ; Starodumov, Andrey ; Šuša, Tatjana ; ... ; Mishra, Saswat ; ... ; Roguljić, Matej ; ... ; Druzhkin, Dmitry (2025) Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC. The European Physical Journal C, 85 . ISSN 1434-6044

	PDF - Published Version - article Available under License Creative Commons Attribution. Download (2MB)
	PDF - Submitted Version - article Available under License Creative Commons Attribution. Download (1MB)

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 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.

Item Type:	Article
Uncontrolled Keywords:	High energy physics; Experimental particle physics; LHC; CMS
Subjects:	NATURAL SCIENCES > Physics > Physics of Elementary Particles and Fields
Divisions:	Centre for detectors, sensors and electronics Division of Experimental Physics
Depositing User:	Ema Buhin Šaler
Date Deposited:	23 Jan 2026 11:08
URI:	http://fulir.irb.hr/id/eprint/11111
DOI:	10.1140/epjc/s10052-025-14713-w

Actions (login required)

View Item