TY - GEN
T1 - A Variational AutoEncoder for Model Independent Searches of New Physics at LHC
AU - Lavizzari, Giulia
AU - Boldrini, Giacomo
AU - Gennai, Simone
AU - Govoni, Pietro
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024/1/1
Y1 - 2024/1/1
N2 - We present a feasibility study for the use of a generative, probabilistic model, a Variational Autoencoder (VAE), to detect deviations from Standard Model (SM) physics in an electroweak process at the Large Hadron Collider (LHC). The new physics responsible for the anomalies is described through an Effective Field Theory (EFT) approach: the SM Lagrangian is Taylor-expanded and the higher order terms cause deviations in the kinematic distributions of the observables, and are thus identified by the model as anomalous contributions with respect to SM. Since the training of the model involves almost only SM events, the proposed strategy is largely independent from any assumption on the nature of the new physics signature. To test the proposed strategy we use parton level generations of Vector Boson Scattering (VBS) events at the LHC, assuming an integrated luminosity of 350 fb - 1.
AB - We present a feasibility study for the use of a generative, probabilistic model, a Variational Autoencoder (VAE), to detect deviations from Standard Model (SM) physics in an electroweak process at the Large Hadron Collider (LHC). The new physics responsible for the anomalies is described through an Effective Field Theory (EFT) approach: the SM Lagrangian is Taylor-expanded and the higher order terms cause deviations in the kinematic distributions of the observables, and are thus identified by the model as anomalous contributions with respect to SM. Since the training of the model involves almost only SM events, the proposed strategy is largely independent from any assumption on the nature of the new physics signature. To test the proposed strategy we use parton level generations of Vector Boson Scattering (VBS) events at the LHC, assuming an integrated luminosity of 350 fb - 1.
KW - Anomaly Detection
KW - Variational AutoEncoder
KW - Vector Boson Scattering
UR - https://www.scopus.com/pages/publications/85184102538
U2 - 10.1007/978-3-031-51023-6_14
DO - 10.1007/978-3-031-51023-6_14
M3 - Conference contribution
AN - SCOPUS:85184102538
SN - 9783031510229
T3 - Lecture Notes in Computer Science
SP - 159
EP - 169
BT - Image Analysis and Processing - ICIAP 2023 Workshops, Proceedings
A2 - Foresti, Gian Luca
A2 - Fusiello, Andrea
A2 - Hancock, Edwin
PB - Springer Science and Business Media Deutschland GmbH
T2 - Workshops hosted by the 22nd International Conference on Image Analysis and Processing, ICIAP 2023
Y2 - 11 September 2023 through 15 September 2023
ER -