BibTex format
@article{Druzhkin:2025:epjc/s10052-025-14713-w,
author = {Druzhkin, D and Borshch, V and Babaev, A and Uzunian, A and Slabospitskii, S and Kachanov, V and Skovpen, Y and Radchenko, O and Kozyrev, A and Dimova, T and Blinov, V and Volkov, P and Savrin, V and Perfilov, M and Klyukhin, V and Gribushin, A and Ershov, A and Dudko, L and Dubinin, M and Bunichev, V and Boos, E and Terkulov, A and Kirakosyan, M and Azarkin, M and Andreev, V and Polikarpov, S and Chistov, R and Chadeeva, M and Zhokin, A and Popov, V and Lychkovskaya, N and Gavrilov, V and Ivanov, K and Aushev, T and Vorobyev, A and Uvarov, L and Sulimov, V and Sosnov, D and Oreshkin, V and Murzin, V and Kim, V and Ivanov, Y and Golovtcov, V and Gavrilov, G and Toropin, A and Tlisova, I and Krasnikov, N and Kirsanov, M and Kirpichnikov, D and Karneyeu, A and Golubev, N and Gninenko, S and Dermenev, A and Andreev, YU and Zhizhin, I and Zarubin, A and Yuldashev, BS and Voytishin, N and Teryaev, O and Smirnov, V and Shulha, S and Shmatov, S and Shalaev, V and Savina, M and Perelygin, V an},
doi = {epjc/s10052-025-14713-w},
journal = {European Physical Journal C},
title = {Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC},
url = {http://dx.doi.org/10.1140/epjc/s10052-025-14713-w},
volume = {85},
year = {2025}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - 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.
AU - Druzhkin,D
AU - Borshch,V
AU - Babaev,A
AU - Uzunian,A
AU - Slabospitskii,S
AU - Kachanov,V
AU - Skovpen,Y
AU - Radchenko,O
AU - Kozyrev,A
AU - Dimova,T
AU - Blinov,V
AU - Volkov,P
AU - Savrin,V
AU - Perfilov,M
AU - Klyukhin,V
AU - Gribushin,A
AU - Ershov,A
AU - Dudko,L
AU - Dubinin,M
AU - Bunichev,V
AU - Boos,E
AU - Terkulov,A
AU - Kirakosyan,M
AU - Azarkin,M
AU - Andreev,V
AU - Polikarpov,S
AU - Chistov,R
AU - Chadeeva,M
AU - Zhokin,A
AU - Popov,V
AU - Lychkovskaya,N
AU - Gavrilov,V
AU - Ivanov,K
AU - Aushev,T
AU - Vorobyev,A
AU - Uvarov,L
AU - Sulimov,V
AU - Sosnov,D
AU - Oreshkin,V
AU - Murzin,V
AU - Kim,V
AU - Ivanov,Y
AU - Golovtcov,V
AU - Gavrilov,G
AU - Toropin,A
AU - Tlisova,I
AU - Krasnikov,N
AU - Kirsanov,M
AU - Kirpichnikov,D
AU - Karneyeu,A
AU - Golubev,N
AU - Gninenko,S
AU - Dermenev,A
AU - Andreev,YU
AU - Zhizhin,I
AU - Zarubin,A
AU - Yuldashev,BS
AU - Voytishin,N
AU - Teryaev,O
AU - Smirnov,V
AU - Shulha,S
AU - Shmatov,S
AU - Shalaev,V
AU - Savina,M
AU - Perelygin,V
AU - Palichik,V
AU - Nikitenko,A
AU - Matveev,V
AU - Malakhov,A
AU - Lanev,A
AU - Korenkov,V
AU - Kodolova,O
AU - Karjavine,V
AU - Gorbunov,I
AU - Golutvin,I
AU - Budkouski,D
AU - Alexakhin,V
AU - Afanasiev,S
AU - Warden,A
AU - Vetens,W
AU - Tsoi,HF
AU - Teague,D
AU - Smith,WH
AU - Sharma,V
AU - Shang,V
AU - Savin,A
AU - Pinna,D
AU - Pétré,L
AU - Parida,G
AU - Mondal,S
AU - Mohammadi,A
AU - Mallampalli,A
AU - Madhusudanan,Sreekala J
AU - Loveless,R
AU - Lanaro,A
AU - Koraka,CK
AU - Herve,A
AU - Herndon,M
AU - He,H
AU - Galloni,C
DO - epjc/s10052-025-14713-w
PY - 2025///
SN - 1434-6044
TI - Development of systematic uncertainty-aware neural network trainings for binned-likelihood analyses at the LHC
T2 - European Physical Journal C
UR - http://dx.doi.org/10.1140/epjc/s10052-025-14713-w
VL - 85
ER -