Approximation Error of Sobolev Regular Functions with tanh Neural Networks: Theoretical Impact on PINNs - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

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

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

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 Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2024), Sep 2024, Vilnius, Lithuania. ⟨hal-04518335⟩
65 Consultations
44 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More