{"ID":2886847,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02275","arxiv_id":"2508.02275","title":"Comparing Generative Models with the New Physics Learning Machine","abstract":"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.","short_abstract":"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-...","url_abs":"https://arxiv.org/abs/2508.02275","url_pdf":"https://arxiv.org/pdf/2508.02275v1","authors":"[\"Samuele Grossi\",\"Marco Letizia\",\"Riccardo Torre\"]","published":"2025-08-04T10:42:52Z","proceeding":"stat.ML","tasks":"[\"stat.ML\",\"cs.LG\",\"hep-ex\",\"hep-ph\"]","methods":"[]","has_code":false}