Evaluating generative models in high energy physics

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversity of California San Diego-
Autor(es): dc.contributorEuropean Center for Nuclear Research (CERN)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorFermilab-
Autor(es): dc.creatorKansal, Raghav-
Autor(es): dc.creatorLi, Anni-
Autor(es): dc.creatorDuarte, Javier-
Autor(es): dc.creatorChernyavskaya, Nadezda-
Autor(es): dc.creatorPierini, Maurizio-
Autor(es): dc.creatorOrzari, Breno-
Autor(es): dc.creatorTomei, Thiago-
Data de aceite: dc.date.accessioned2025-08-21T19:09:25Z-
Data de disponibilização: dc.date.available2025-08-21T19:09:25Z-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-04-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1103/PhysRevD.107.076017-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/247328-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/247328-
Descrição: dc.descriptionThere has been a recent explosion in research into machine-learning-based generative modeling to tackle computational challenges for simulations in high energy physics (HEP). In order to use such alternative simulators in practice, we need well-defined metrics to compare different generative models and evaluate their discrepancy from the true distributions. We present the first systematic review and investigation into evaluation metrics and their sensitivity to failure modes of generative models, using the framework of two-sample goodness-of-fit testing, and their relevance and viability for HEP. Inspired by previous work in both physics and computer vision, we propose two new metrics, the Fréchet and kernel physics distances (FPD and KPD, respectively) and perform a variety of experiments measuring their performance on simple Gaussian-distributed and simulated high energy jet datasets. We find FPD, in particular, to be the most sensitive metric to all alternative jet distributions tested and recommend its adoption, along with the KPD and Wasserstein distances between individual feature distributions, for evaluating generative models in HEP. We finally demonstrate the efficacy of these proposed metrics in evaluating and comparing a novel attention-based generative adversarial particle transformer to the state-of-the-art message-passing generative adversarial network jet simulation model. The code for our proposed metrics is provided in the open source jetnet python library.-
Descrição: dc.descriptionUniversity of California San Diego-
Descrição: dc.descriptionEuropean Center for Nuclear Research (CERN)-
Descrição: dc.descriptionUniversidade Estadual Paulista, SP-
Descrição: dc.descriptionFermilab-
Descrição: dc.descriptionUniversidade Estadual Paulista, SP-
Idioma: dc.languageen-
Relação: dc.relationPhysical Review D-
???dc.source???: dc.sourceScopus-
Título: dc.titleEvaluating generative models in high energy physics-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.