Cargando…

Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event represe...

Descripción completa

Detalles Bibliográficos
Autores principales: Jawahar, Pratik, Aarrestad, Thea, Chernyavskaya, Nadezda, Pierini, Maurizio, Wozniak, Kinga A., Ngadiuba, Jennifer, Duarte, Javier, Tsan, Steven
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8919050/
https://www.ncbi.nlm.nih.gov/pubmed/35295683
http://dx.doi.org/10.3389/fdata.2022.803685
Descripción
Sumario:We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event representations, anomaly score definitions, network architectures) affect the result on specific benchmark new physics models. Once a baseline is established, we discuss how to improve the anomaly detection accuracy by exploiting normalizing flow layers in the latent space of the variational autoencoder.