English

GANplifying Event Samples

High Energy Physics - Phenomenology 2021-06-11 v3 High Energy Physics - Experiment Data Analysis, Statistics and Probability Machine Learning

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.

Keywords

Cite

@article{arxiv.2008.06545,
  title  = {GANplifying Event Samples},
  author = {Anja Butter and Sascha Diefenbacher and Gregor Kasieczka and Benjamin Nachman and Tilman Plehn},
  journal= {arXiv preprint arXiv:2008.06545},
  year   = {2021}
}

Comments

15 pages, 7 figures, fixed two equations, extended acknowledgments, addressed referee comments, improved figure readability

R2 v1 2026-06-23T17:52:13.617Z