Learning new physics efficiently with nonparametric methods

TL;DR

This paper introduces a nonparametric machine learning method using kernel techniques for efficient, model-independent searches for new physics in experimental data, offering advantages over neural networks in training speed and resource use.

Contribution

The authors adapt kernel-based nonparametric learning algorithms for hypothesis testing in new physics searches, demonstrating improved efficiency and scalability over neural network approaches.

Findings

Achieves comparable performance to neural networks

Significantly reduces training times and computational resources

Successfully applied to higher-dimensional datasets

Abstract

We present a machine learning approach for model-independent new physics searches. The corresponding algorithm is powered by recent large-scale implementations of kernel methods, nonparametric learning algorithms that can approximate any continuous function given enough data. Based on the original proposal by D'Agnolo and Wulzer (arXiv:1806.02350), the model evaluates the compatibility between experimental data and a reference model, by implementing a hypothesis testing procedure based on the likelihood ratio. Model-independence is enforced by avoiding any prior assumption about the presence or shape of new physics components in the measurements. We show that our approach has dramatic advantages compared to neural network implementations in terms of training times and computational resources, while maintaining comparable performances. In particular, we conduct our tests on higher dimensional datasets, a step forward with respect to previous studies.