Compressing PDF sets using generative adversarial networks

TL;DR

This paper introduces a novel PDF compression method using GANs to generate synthetic replicas, reducing the number of replicas needed while maintaining distribution accuracy, and explores GANs as an alternative to traditional fitting methods.

Contribution

The paper presents a GAN-based approach for PDF set compression that enhances statistical representation and reduces replica count, offering an alternative to traditional fitting techniques.

Findings

GAN-generated replicas improve PDF set compression

Reduced number of replicas needed for accurate distribution

GANs can potentially replace large-scale fitting processes

Abstract

We present a compression algorithm for parton densities using synthetic replicas generated from the training of a Generative Adversarial Network (GAN). The generated replicas are used to further enhance the statistics of a given Monte Carlo PDF set prior to compression. This results in a compression methodology that is able to provide a compressed set with smaller number of replicas and a more adequate representation of the original probability distribution. We also address the question of whether the GAN could be used as an alternative mechanism to avoid the fitting of large number of replicas.