Towards the compression of parton densities through machine learning algorithms

TL;DR

This paper explores machine learning techniques to compress and improve the combination of parton density functions, aiming to enhance the efficiency and accuracy of PDF uncertainty estimations in high-energy physics.

Contribution

It introduces a novel machine learning-based clustering approach for Monte Carlo PDF compression, advancing the methods for combining PDF sets.

Findings

Machine learning clustering effectively compresses PDF sets.

The new approach maintains accuracy while reducing computational complexity.

Enhanced PDF uncertainty estimation through improved compression techniques.

Abstract

One of the most fascinating challenges in the context of parton density function (PDF) is the determination of the best combined PDF uncertainty from individual PDF sets. Since 2014 multiple methodologies have been developed to achieve this goal. In this proceedings we first summarize the strategy adopted by the PDF4LHC15 recommendation and then, we discuss about a new approach to Monte Carlo PDF compression based on clustering through machine learning algorithms.