Comparing Generative Models with the New Physics Learning Machine

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Grossi, Samuele, Letizia, Marco, Torre, Riccardo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915425420312576
author Grossi, Samuele
Letizia, Marco
Torre, Riccardo
author_facet Grossi, Samuele
Letizia, Marco
Torre, Riccardo
contents The rise of generative models for scientific research calls for the development of new methods to evaluate their fidelity. A natural framework for addressing this problem is two-sample hypothesis testing, namely the task of determining whether two data sets are drawn from the same distribution. In large-scale and high-dimensional regimes, machine learning offers a set of tools to push beyond the limitations of standard statistical techniques. In this work, we put this claim to the test by comparing a recent proposal from the high-energy physics literature, the New Physics Learning Machine, to perform a classification-based two-sample test against a number of alternative approaches, following the framework presented in Grossi et al. (2025). We highlight the efficiency tradeoffs of the method and the computational costs that come from adopting learning-based approaches. Finally, we discuss the advantages of the different methods for different use cases.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02275
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparing Generative Models with the New Physics Learning Machine
Grossi, Samuele
Letizia, Marco
Torre, Riccardo
Machine Learning
High Energy Physics - Experiment
High Energy Physics - Phenomenology
The rise of generative models for scientific research calls for the development of new methods to evaluate their fidelity. A natural framework for addressing this problem is two-sample hypothesis testing, namely the task of determining whether two data sets are drawn from the same distribution. In large-scale and high-dimensional regimes, machine learning offers a set of tools to push beyond the limitations of standard statistical techniques. In this work, we put this claim to the test by comparing a recent proposal from the high-energy physics literature, the New Physics Learning Machine, to perform a classification-based two-sample test against a number of alternative approaches, following the framework presented in Grossi et al. (2025). We highlight the efficiency tradeoffs of the method and the computational costs that come from adopting learning-based approaches. Finally, we discuss the advantages of the different methods for different use cases.
title Comparing Generative Models with the New Physics Learning Machine
topic Machine Learning
High Energy Physics - Experiment
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2508.02275