Exotic and physics-informed support vector machines for high energy physics

TL;DR

This paper introduces two novel support vector machine approaches, exotic and physics-informed, tailored for high-energy physics data analysis, demonstrating the effectiveness of physics-informed models in distinguishing signal from background events.

Contribution

The paper presents the first integration of physics dynamics into support vector machines for high-energy physics, improving event classification accuracy.

Findings

Physics-informed SVMs outperform traditional methods

Physics integration enhances classification accuracy

Simulated Drell-Yan event tests validate approaches

Abstract

In this article, we explore machine learning techniques using support vector machines with two novel approaches: exotic and physics-informed support vector machines. Exotic support vector machines employ unconventional techniques such as genetic algorithms and boosting. Physics-informed support vector machines integrate the physics dynamics of a given high-energy physics process in a straightforward manner. The goal is to efficiently distinguish signal and background events in high-energy physics collision data. To test our algorithms, we perform computational experiments with simulated Drell-Yan events in proton-proton collisions. Our results highlight the superiority of the physics-informed support vector machines, emphasizing their potential in high-energy physics and promoting the inclusion of physics information in machine learning algorithms for future research.