Parameterized Machine Learning for High-Energy Physics

TL;DR

This paper introduces parameterized classifiers in high-energy physics that incorporate physics parameters as inputs, enabling smooth interpolation between models and improved performance across varying conditions.

Contribution

The paper presents a novel approach to machine learning classifiers that include physics parameters, simplifying training and enhancing performance across parameter ranges.

Findings

Parameterized classifiers interpolate smoothly between different physics parameters.

The approach improves classification performance at intermediate parameter values.

Implementation is straightforward and enhances model flexibility.

Abstract

We investigate a new structure for machine learning classifiers applied to problems in high-energy physics by expanding the inputs to include not only measured features but also physics parameters. The physics parameters represent a smoothly varying learning task, and the resulting parameterized classifier can smoothly interpolate between them and replace sets of classifiers trained at individual values. This simplifies the training process and gives improved performance at intermediate values, even for complex problems requiring deep learning. Applications include tools parameterized in terms of theoretical model parameters, such as the mass of a particle, which allow for a single network to provide improved discrimination across a range of masses. This concept is simple to implement and allows for optimized interpolatable results.