Interpretable Machine Learning Methods Applied to Jet Background Subtraction in Heavy Ion Collisions
High Energy Physics - Experiment
2024-03-12 v2 Nuclear Experiment
Abstract
Jet measurements in heavy ion collisions can provide constraints on the properties of the quark gluon plasma, but the kinematic reach is limited by a large, fluctuating background. We present a novel application of symbolic regression to extract a functional representation of a deep neural network trained to subtract the background for measurements of jets in relativistic heavy ion collisions. We show that the deep neural network is approximately the same as a method using the particle multiplicity in a jet. This demonstrates that interpretable machine learning methods can provide insight into underlying physical processes.
Cite
@article{arxiv.2303.08275,
title = {Interpretable Machine Learning Methods Applied to Jet Background Subtraction in Heavy Ion Collisions},
author = {Tanner Mengel and Patrick Steffanic and Charles Hughes and Antonio Carlos Oliveira da Silva and Christine Nattrass},
journal= {arXiv preprint arXiv:2303.08275},
year = {2024}
}