SciPost Submission Page

GANplifying Event Samples

by Anja Butter, Sascha Diefenbacher, Gregor Kasieczka, Benjamin Nachman, Tilman Plehn

Submission summary

As Contributors: Sascha Diefenbacher · Tilman Plehn
Arxiv Link: https://arxiv.org/abs/2008.06545v2 (pdf)
Date submitted: 2020-09-17 16:02
Submitted by: Diefenbacher, Sascha
Submitted to: SciPost Physics
Academic field: Physics
Specialties:
  • High-Energy Physics - Experiment
  • High-Energy Physics - Phenomenology
Approaches: Computational, Phenomenological

Abstract

A critical question concerning generative networks applied to event generation in particle physics is if the generated events add statistical precision beyond the training sample. We show for a simple example with increasing dimensionality how generative networks indeed amplify the training statistics. We quantify their impact through an amplification factor or equivalent numbers of sampled events.

Current status:
Editor-in-charge assigned


Submission & Refereeing History

You are currently on this page

Submission 2008.06545v2 on 17 September 2020

Login to report or comment