Pileup Mitigation with Machine Learning (PUMML)

TL;DR

This paper introduces PUMML, a machine learning-based method using convolutional neural networks to effectively remove pileup contamination from energy measurements in particle physics experiments, improving the accuracy of jet observables.

Contribution

The paper presents a novel CNN-based algorithm for pileup mitigation that outperforms existing methods and can be trained directly on data for practical application.

Findings

PUMML effectively reduces pileup distortion across various jet observables.

The method demonstrates robustness against different pileup conditions.

It can be trained directly on experimental data.

Abstract

Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data.