We discuss the determination of the parton substructure of hadrons by casting it as a peculiar form of pattern recognition problem in which the pattern is a probability distribution, and we present the way this problem has been tackled and solved. Specifically, we review the NNPDF approach to PDF determination, which is based on the combination of a Monte Carlo approach with neural networks as basic underlying interpolators. We discuss the current NNPDF methodology, based on genetic minimization, and its validation through closure testing. We then present recent developments in which a hyperoptimized deep-learning framework for PDF determination is being developed, optimized, and tested.

Parton distribution functions / S. Forte, S. Carrazza - In: Artificial Intelligence For High Energy Physics / [a cura di] P. Calafiura, D. Rousseau, K. Terao. - [s.l] : World Scientific, 2022. - ISBN 978-981-12-3402-6. - pp. 715-762 [10.1142/9789811234033_0019]

Parton distribution functions

S. Forte;S. Carrazza
2022

Abstract

We discuss the determination of the parton substructure of hadrons by casting it as a peculiar form of pattern recognition problem in which the pattern is a probability distribution, and we present the way this problem has been tackled and solved. Specifically, we review the NNPDF approach to PDF determination, which is based on the combination of a Monte Carlo approach with neural networks as basic underlying interpolators. We discuss the current NNPDF methodology, based on genetic minimization, and its validation through closure testing. We then present recent developments in which a hyperoptimized deep-learning framework for PDF determination is being developed, optimized, and tested.
Settore FIS/02 - Fisica Teorica, Modelli e Metodi Matematici
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
   Proton strucure for discovery at the Large Hadron Collider (NNNPDF)
   NNNPDF
   EUROPEAN COMMISSION
   H2020
   740006
2022
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
2008.12305.pdf

accesso aperto

Tipologia: Pre-print (manoscritto inviato all'editore)
Dimensione 2.3 MB
Formato Adobe PDF
2.3 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/2434/956082
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact