Approximation Error of Sobolev Regular Functions with tanh Neural Networks: Theoretical Impact on PINNs - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail (Preprint/Prepublication) Année : 2024

Approximation Error of Sobolev Regular Functions with tanh Neural Networks: Theoretical Impact on PINNs

Benjamin Girault
Connectez-vous pour contacter l'auteur
Jordan Patracone
  • Fonction : Auteur
  • PersonId : 1366866
Marc Sebban

Résumé

Considering the key role played by derivatives in Partial Differential Equations (PDEs), using the tanh activation function in Physics-Informed Neural Networks(PINNs) yields useful smoothness properties to derive theoretical guarantees in Sobolev norm. In this paper, we conduct an extensive functional analysis, unveiling tighter approximation bounds compared to prior works, especially for higher order PDEs. These better guarantees translate into smaller PINN architectures and improved generalization error with arbitrarily small Sobolev norms of the PDE residuals.
Fichier principal
Vignette du fichier
ECML2024-Girault.pdf (719.12 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04518335 , version 1 (23-03-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04518335 , version 1

Citer

Benjamin Girault, Rémi Emonet, Amaury Habrard, Jordan Patracone, Marc Sebban. Approximation Error of Sobolev Regular Functions with tanh Neural Networks: Theoretical Impact on PINNs. 2024. ⟨hal-04518335⟩
5 Consultations
2 Téléchargements

Partager

Gmail Facebook X LinkedIn More