Generative networks for precision enthusiasts

Generative networks are opening new avenues in fast event generation for the LHC. We show how generative flow networks can reach percent-level precision for kinematic distributions, how they can be trained jointly with a discriminator, and how this discriminator improves the generation. Our joint tr...

Full description

Saved in:
Bibliographic Details
Published inSciPost physics Vol. 14; no. 4; p. 078
Main Authors Butter, Anja, Heimel, Theo, Hummerich, Sander, Krebs, Tobias, Plehn, Tilman, Rousselot, Armand, Vent, Sophia
Format Journal Article
LanguageEnglish
Published SciPost 01.04.2023
Online AccessGet full text

Cover

More Information
Summary:Generative networks are opening new avenues in fast event generation for the LHC. We show how generative flow networks can reach percent-level precision for kinematic distributions, how they can be trained jointly with a discriminator, and how this discriminator improves the generation. Our joint training relies on a novel coupling of the two networks which does not require a Nash equilibrium. We then estimate the generation uncertainties through a Bayesian network setup and through conditional data augmentation, while the discriminator ensures that there are no systematic inconsistencies compared to the training data.
ISSN:2542-4653
2542-4653
DOI:10.21468/SciPostPhys.14.4.078