A factorisation-aware Matrix element emulator

Abstract In this article we present a neural network based model to emulate matrix elements. This model improves on existing methods by taking advantage of the known factorisation properties of matrix elements. In doing so we can control the behaviour of simulated matrix elements when extrapolating...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: D. Maître, H. Truong
Formato: article
Lenguaje:EN
Publicado: SpringerOpen 2021
Materias:
Acceso en línea:https://doaj.org/article/586a39d7e38e4044bcd62be0948fce6c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:586a39d7e38e4044bcd62be0948fce6c
record_format dspace
spelling oai:doaj.org-article:586a39d7e38e4044bcd62be0948fce6c2021-11-14T12:40:55ZA factorisation-aware Matrix element emulator10.1007/JHEP11(2021)0661029-8479https://doaj.org/article/586a39d7e38e4044bcd62be0948fce6c2021-11-01T00:00:00Zhttps://doi.org/10.1007/JHEP11(2021)066https://doaj.org/toc/1029-8479Abstract In this article we present a neural network based model to emulate matrix elements. This model improves on existing methods by taking advantage of the known factorisation properties of matrix elements. In doing so we can control the behaviour of simulated matrix elements when extrapolating into more singular regions than the ones used for training the neural network. We apply our model to the case of leading-order jet production in e + e − collisions with up to five jets. Our results show that this model can reproduce the matrix elements with errors below the one-percent level on the phase-space covered during fitting and testing, and a robust extrapolation to the parts of the phase-space where the matrix elements are more singular than seen at the fitting stage.D. MaîtreH. TruongSpringerOpenarticlePerturbative QCDScattering AmplitudesNuclear and particle physics. Atomic energy. RadioactivityQC770-798ENJournal of High Energy Physics, Vol 2021, Iss 11, Pp 1-24 (2021)
institution DOAJ
collection DOAJ
language EN
topic Perturbative QCD
Scattering Amplitudes
Nuclear and particle physics. Atomic energy. Radioactivity
QC770-798
spellingShingle Perturbative QCD
Scattering Amplitudes
Nuclear and particle physics. Atomic energy. Radioactivity
QC770-798
D. Maître
H. Truong
A factorisation-aware Matrix element emulator
description Abstract In this article we present a neural network based model to emulate matrix elements. This model improves on existing methods by taking advantage of the known factorisation properties of matrix elements. In doing so we can control the behaviour of simulated matrix elements when extrapolating into more singular regions than the ones used for training the neural network. We apply our model to the case of leading-order jet production in e + e − collisions with up to five jets. Our results show that this model can reproduce the matrix elements with errors below the one-percent level on the phase-space covered during fitting and testing, and a robust extrapolation to the parts of the phase-space where the matrix elements are more singular than seen at the fitting stage.
format article
author D. Maître
H. Truong
author_facet D. Maître
H. Truong
author_sort D. Maître
title A factorisation-aware Matrix element emulator
title_short A factorisation-aware Matrix element emulator
title_full A factorisation-aware Matrix element emulator
title_fullStr A factorisation-aware Matrix element emulator
title_full_unstemmed A factorisation-aware Matrix element emulator
title_sort factorisation-aware matrix element emulator
publisher SpringerOpen
publishDate 2021
url https://doaj.org/article/586a39d7e38e4044bcd62be0948fce6c
work_keys_str_mv AT dmaitre afactorisationawarematrixelementemulator
AT htruong afactorisationawarematrixelementemulator
AT dmaitre factorisationawarematrixelementemulator
AT htruong factorisationawarematrixelementemulator
_version_ 1718429106818777088