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

Frontiers in Big Data

Javier Duarte¹  Steven Tsan¹  Pratik Jawahar²  Thea Aarrestad²  Maurizio Pierini²  Nadezda Chernyavskaya²  Kinga A. Wozniak³  Jennifer Ngadiuba⁴ 

[1] Department of Physics, University of California, San Diego, San Diego, CA, United States;Experimental Physics Department, European Center for Nuclear Research (CERN), Geneva, Switzerland;Faculty of Computer Science, University of Vienna, Vienna, Austria;Lauritsen Laboratory of High Energy Physics, California Institute of Technology, Pasadena, CA, United States;Particle Physics Division, Fermi National Accelerator Laboratory (FNAL), Batavia, IL, United States;

关键词: anomaly detection (AD);    variational auto encoder (VAE);    normalizing flow (NF);    Large Hadron Collider (LHC);    new physics beyond standard model;    graph convolutional network (GCN);   

DOI  :  10.3389/fdata.2022.803685

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown