Enregistré dans:
Détails bibliographiques
Auteurs principaux: Calisto, Francesco, Moodie, Ryan, Zoia, Simone
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2312.02067
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911964468346880
author Calisto, Francesco
Moodie, Ryan
Zoia, Simone
author_facet Calisto, Francesco
Moodie, Ryan
Zoia, Simone
contents We perform an exploratory study of a new approach for evaluating Feynman integrals numerically. We apply the recently-proposed framework of physics-informed deep learning to train neural networks to approximate the solution to the differential equations satisfied by the Feynman integrals. This approach relies neither on a canonical form of the differential equations, which is often a bottleneck for the analytical techniques, nor on the availability of a large dataset, and after training yields essentially instantaneous evaluation times. We provide a proof-of-concept implementation within the PyTorch framework, and apply it to a number of one- and two-loop examples, achieving a mean magnitude of relative difference of around 1% at two loops in the physical phase space with network training times on the order of an hour on a laptop GPU.
format Preprint
id arxiv_https___arxiv_org_abs_2312_02067
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning Feynman integrals from differential equations with neural networks
Calisto, Francesco
Moodie, Ryan
Zoia, Simone
High Energy Physics - Phenomenology
High Energy Physics - Theory
We perform an exploratory study of a new approach for evaluating Feynman integrals numerically. We apply the recently-proposed framework of physics-informed deep learning to train neural networks to approximate the solution to the differential equations satisfied by the Feynman integrals. This approach relies neither on a canonical form of the differential equations, which is often a bottleneck for the analytical techniques, nor on the availability of a large dataset, and after training yields essentially instantaneous evaluation times. We provide a proof-of-concept implementation within the PyTorch framework, and apply it to a number of one- and two-loop examples, achieving a mean magnitude of relative difference of around 1% at two loops in the physical phase space with network training times on the order of an hour on a laptop GPU.
title Learning Feynman integrals from differential equations with neural networks
topic High Energy Physics - Phenomenology
High Energy Physics - Theory
url https://arxiv.org/abs/2312.02067