Towards Machine Learning Analytics for Jet Substructure

TL;DR

This paper explores integrating expert knowledge into machine learning models for jet substructure analysis, aiming to improve interpretability and performance in classifying quark and gluon jets using simplified observables and analytical methods.

Contribution

It introduces a new, more theoretically transparent version of N-subjettiness and analytically studies a perceptron’s performance in jet classification tasks.

Findings

The new N-subjettiness maintains or improves discrimination power.

Analytical conditions for perceptron optimal performance are identified.

Good agreement between analytical predictions and neural network implementations.

Abstract

The past few years have seen a rapid development of machine-learning algorithms. While surely augmenting performance, these complex tools are often treated as black-boxes and may impair our understanding of the physical processes under study. The aim of this paper is to move a first step into the direction of applying expert-knowledge in particle physics to calculate the optimal decision function and test whether it is achieved by standard training, thus making the aforementioned black-box more transparent. In particular, we consider the binary classification problem of discriminating quark-initiated jets from gluon-initiated ones. We construct a new version of the widely used N-subjettiness, which features a simpler theoretical behaviour than the original one, while maintaining, if not exceeding, the discrimination power. We input these new observables to the simplest possible neural network, i.e. the one made by a single neuron, or perceptron, and we analytically study the network behaviour at leading logarithmic accuracy. We are able to determine under which circumstances the perceptron achieves optimal performance. We also compare our analytic findings to an actual implementation of a perceptron and to a more realistic neural network and find very good agreement.