Deep Neural Network Structures Solving Variational Inequalities * - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Set-Valued and Variational Analysis Année : 2020

Deep Neural Network Structures Solving Variational Inequalities *

Résumé

Motivated by structures that appear in deep neural networks, we investigate nonlinear composite models alternating proximity and affine operators defined on different spaces. We first show that a wide range of activation operators used in neural networks are actually proximity operators. We then establish conditions for the averagedness of the proposed composite constructs and investigate their asymptotic properties. It is shown that the limit of the resulting process solves a variational inequality which, in general, does not derive from a minimization problem. The analysis relies on tools from monotone operator theory and sheds some light on a class of neural networks structures with so far elusive asymptotic properties.
Fichier principal
Vignette du fichier
svva5.pdf (500.54 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02425025 , version 1 (29-12-2019)

Identifiants

Citer

Patrick L Combettes, Jean-Christophe Pesquet. Deep Neural Network Structures Solving Variational Inequalities *. Set-Valued and Variational Analysis, In press, ⟨10.1007/s11228-019-00526-z⟩. ⟨hal-02425025⟩
95 Consultations
125 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More