Leveraging Machine Learning for Jet Energy Reconstruction in Heavy Ion Collisions

In understanding the effects of quark-gluon plasma on jet spectra in heavy ion collisions, it is essential to have accurate values of jet energy. Machine learning is increasingly prevalent in high energy physics, but is it a reliable tool for jet physics, and what are the best applications for it? We have reproduced the results from [Phys.Rev.C 99 (2019) 6, 064904, Machine-learning-based jet momentum reconstruction in heavy-ion collisions], and extend them to include kinematics relevant for sPHENIX collision energies at RHIC. We also evaluate potential biases in the algorithm and how to mitigate them. Our study aims to contribute to the broader trend of embracing machine learning, and to delineate appropriate domains for its use.