KIT | KIT-Bibliothek | Impressum | Datenschutz

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

CMS Collaboration; Chekhovsky, V.; Hayrapetyan, A.; Makarenko, V.; Tumasyan, A.; Adam, W.; Andrejkovic, J. W.; Benato, L.; Bergauer, T.; Dimova, Tatyana V.; Chatterjee, S.; Damanakis, K.; Dragicevic, M.; Hussain, P. S.; Jeitler, M.; Krammer, N.; Li, A.; Liko, D.; Mikulec, I.; ... mehr

Abstract (englisch):

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.


Verlagsausgabe §
DOI: 10.5445/IR/1000189265
Veröffentlicht am 23.12.2025
Originalveröffentlichung
DOI: 10.1140/epjc/s10052-025-14713-w
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Astroteilchenphysik (IAP)
Institut für Experimentelle Teilchenphysik (ETP)
Institut für Prozessdatenverarbeitung und Elektronik (IPE)
Scientific Computing Center (SCC)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2025
Sprache Englisch
Identifikator ISSN: 1434-6044, 1434-6052
KITopen-ID: 1000189265
Erschienen in The European Physical Journal C
Verlag Springer-Verlag
Band 85
Heft 11
Seiten 1360
Vorab online veröffentlicht am 26.11.2025
Schlagwörter Experimental Particle Physics, Machine Learning, Neural decoding, Particle Physics, Statistical Learning, Artificial Intelligence
Nachgewiesen in Scopus
OpenAlex
KIT – Die Universität in der Helmholtz-Gemeinschaft
KITopen Landing Page