Trees versus Neural Networks for enhancing tau lepton real-time selection in proton-proton collisions

TL;DR

This paper compares decision trees and neural networks for real-time tau lepton detection in proton-proton collisions, demonstrating improved performance and lower energy thresholds, which enhances the sensitivity of new physics searches.

Contribution

It introduces supervised learning methods, including decision trees and neural networks, for tau lepton trigger optimization in collider experiments, showing their advantages over standard triggers.

Findings

Decision trees and neural networks outperform traditional threshold triggers.

Neural networks can further improve trigger efficiency.

Lower energy thresholds increase sensitivity to new phenomena.

Abstract

This paper introduces supervised learning techniques for real-time selection (triggering) of hadronically decaying tau leptons in proton-proton colliders. By implementing classic machine learning decision trees and advanced deep learning models, such as Multi-Layer Perceptron or residual neural networks, visible improvements in performance compared to standard threshold tau triggers are observed. We show how such an implementation may lower selection energy thresholds, thus contributing to increasing the sensitivity of searches for new phenomena in proton-proton collisions classified by low-energy tau leptons. Moreover, we analyze when it is better to use neural networks versus decision trees for tau triggers with conclusions relevant to other problems in physics.