Support Vector Machines and Generalisation in HEP

TL;DR

This paper reviews support vector machines (SVMs) in high energy physics, highlighting their advantages over neural networks and decision trees in reducing overfitting, and discusses improvements in SVM tools and cross validation techniques.

Contribution

It introduces new tools for SVMs and cross validation within the TMVA framework, enhancing their application in particle physics analyses.

Findings

SVMs are less susceptible to overfitting than neural networks and decision trees.

Cross validation improves the generalisation of multivariate algorithms in HEP.

Enhanced SVM tools are integrated into the TMVA framework for better analysis.

Abstract

We review the concept of support vector machines (SVMs) and discuss examples of their use. One of the benefits of SVM algorithms, compared with neural networks and decision trees is that they can be less susceptible to over fitting than those other algorithms are to over training. This issue is related to the generalisation of a multivariate algorithm (MVA); a problem that has often been overlooked in particle physics. We discuss cross validation and how this can be used to improve the generalisation of a MVA in the context of High Energy Physics analyses. The examples presented use the Toolkit for Multivariate Analysis (TMVA) based on ROOT and describe our improvements to the SVM functionality and new tools introduced for cross validation within this framework.