We present a new regression model for the determination of parton distribution functions (PDF) using techniques inspired from deep learning projects. In the context of the NNPDF methodology, we implement a new efficient computing framework based on graph generated models for PDF parametrization and gradient descent optimization. The best model configuration is derived from a robust cross-validation mechanism through a hyperparametrization tune procedure. We show that results provided by this new framework outperforms the current state-of-the-art PDF fitting methodology in terms of best model selection and computational resources usage.

Towards a new generation of parton densities with deep learning models / S. Carrazza, C. Juan. - In: THE EUROPEAN PHYSICAL JOURNAL. C, PARTICLES AND FIELDS. - ISSN 1434-6044. - 79:8(2019 Aug 13). [10.1140/epjc/s10052-019-7197-2]

Towards a new generation of parton densities with deep learning models

S. Carrazza
Primo
;
C. Juan
Ultimo
2019

Abstract

We present a new regression model for the determination of parton distribution functions (PDF) using techniques inspired from deep learning projects. In the context of the NNPDF methodology, we implement a new efficient computing framework based on graph generated models for PDF parametrization and gradient descent optimization. The best model configuration is derived from a robust cross-validation mechanism through a hyperparametrization tune procedure. We show that results provided by this new framework outperforms the current state-of-the-art PDF fitting methodology in terms of best model selection and computational resources usage.
Settore FIS/02 - Fisica Teorica, Modelli e Metodi Matematici
Proton strucure for discovery at the Large Hadron Collider (NNNPDF)
Article (author)
File in questo prodotto:
File Dimensione Formato  
Carrazza-Cruz-Martinez2019_Article_TowardsANewGenerationOfPartonD.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 1.45 MB
Formato Adobe PDF
1.45 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/674396
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 13
social impact