Bregman Proximal Viewpoint on Neural Operators - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Bregman Proximal Viewpoint on Neural Operators

Résumé

We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems over Banach function spaces. The proposed framework allows interpreting the activation operators as Bregman proximity operators from dual to primal space. This novel viewpoint is general enough to recover classical neural operators as well as a new variant, coined Bregman neural operators, which includes a skip-like connection and features the same expressivity of standard neural operators. Numerical experiments support the added benefits of the Bregman variant of Fourier neural operators for training deeper and more accurate models.
Fichier principal
Vignette du fichier
A_Proximal_Viewpoint_on_Neural_Operators-7.pdf (701.52 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04584456 , version 1 (23-05-2024)
hal-04584456 , version 2 (06-06-2024)

Licence

Identifiants

  • HAL Id : hal-04584456 , version 2

Citer

Abdel-Rahim Mezidi, Jordan Frecon, Saverio Salzo, Amaury Habrard, Massimiliano Pontil, et al.. Bregman Proximal Viewpoint on Neural Operators. 2024. ⟨hal-04584456v2⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More