A Block-Coordinate Approach of Multi-level Optimization with an Application to Physics-Informed Neural Networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

A Block-Coordinate Approach of Multi-level Optimization with an Application to Physics-Informed Neural Networks

Résumé

Multi-level methods are widely used for the solution of large-scale problems, because of their computational advantages and exploitation of the complementarity between the involved sub-problems. After a re-interpretation of multi-level methods from a block-coordinate point of view, we propose a multi-level algorithm for the solution of nonlinear optimization problems and analyze its evaluation complexity. We apply it to the solution of partial differential equations using physics-informed neural networks (PINNs) and show on a few test problems that the approach results in better solutions and significant computational savings.
Fichier principal
Vignette du fichier
MPINNSv1.pdf (3.2 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04104450 , version 1 (24-05-2023)

Identifiants

  • HAL Id : hal-04104450 , version 1

Citer

Serge Gratton, Valentin Mercier, Elisa Riccietti, Philippe L Toint. A Block-Coordinate Approach of Multi-level Optimization with an Application to Physics-Informed Neural Networks. 2023. ⟨hal-04104450⟩
119 Consultations
42 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More