Particle-based fast jet simulation at the LHC with variational autoencoders

Journal Article · 12 July 2022 · Machine Learning: Science and Technology

DOI: https://doi.org/10.1088/2632-2153/ac7c56 · OSTI ID:1875993

Touranakou, Mary ; Chernyavskaya, Nadezda ; Duarte, Javier ; Gunopulos, Dimitrios ; Kansal, Raghav ; Orzari, Breno ; Pierini, Maurizio ; Tomei, Thiago ; Vlimant, Jean-Roch

Abstract We study how to use deep variational autoencoders (VAEs) for a fast simulation of jets of particles at the Large Hadron Collider. We represent jets as a list of constituents, characterized by their momenta. Starting from a simulation of the jet before detector effects, we train a deep VAE to return the corresponding list of constituents after detection. Doing so, we bypass both the time-consuming detector simulation and the collision reconstruction steps of a traditional processing chain, speeding up significantly the events generation workflow. Through model optimization and hyperparameter tuning, we achieve state-of-the-art precision on the jet four-momentum, while providing an accurate description of the constituents momenta, and an inference time comparable to that of a rule-based fast simulation.

• Research Organization: California Institute of Technology (CalTech), Pasadena, CA (United States); University of California, San Diego, CA (United States)
• Sponsoring Organization: European Union’s Horizon 2020; National Science Foundation (NSF); Sao Paulo Research Foundation (FAPESP); USDOE; USDOE Office of Science (SC), High Energy Physics (HEP); University of California Office of the President
• Grant/Contract Number: AC02-07CH11359; SC0011925; SC0019227; SC0021187
• OSTI ID: 1875993
• Report Number(s): FERMILAB-PUB-22-954-V; arXiv:2203.00520
• Journal Information: Machine Learning: Science and Technology, Journal Name: Machine Learning: Science and Technology Journal Issue: 3 Vol. 3; ISSN 2632-2153
• Publisher: IOP PublishingCopyright Statement
• Country of Publication: United Kingdom
• Language: English