Pileup Subtraction and Jet Energy Prediction Using Machine Learning

TL;DR

This paper explores machine learning techniques to improve jet energy estimation in LHC experiments by selecting key features and applying models like linear regression, resulting in significant performance improvements.

Contribution

It introduces a feature selection approach combined with machine learning models to enhance jet energy prediction accuracy in high-energy physics.

Findings

Linear regression with selected features outperforms baseline methods

Significant improvement in jet energy prediction accuracy

Support vector regression and decision trees were also evaluated

Abstract

In the Large Hardron Collider (LHC), multiple proton-proton collisions cause pileup in reconstructing energy information for a single primary collision (jet). This project aims to select the most important features and create a model to accurately estimate jet energy. Different machine learning methods were explored, including linear regression, support vector regression and decision tree. The best result is obtained by linear regression with predictive features and the performance is improved significantly from the baseline method.