Mean-field Langevin System, Optimal Control and Deep Neural Networks - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Mean-field Langevin System, Optimal Control and Deep Neural Networks

Résumé

In this paper, we study a regularised relaxed optimal control problem and, in particular, we are concerned with the case where the control variable is of large dimension. We introduce a system of mean-field Langevin equations, the invariant measure of which is shown to be the optimal control of the initial problem under mild conditions. Therefore, this system of processes can be viewed as a continuous-time numerical algorithm for computing the optimal control. As an application, this result endorses the solvability of the stochastic gradient descent algorithm for a wide class of deep neural networks.
Fichier principal
Vignette du fichier
Langevin system arXiv.pdf (400.87 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02291488 , version 1 (18-09-2019)

Identifiants

  • HAL Id : hal-02291488 , version 1

Citer

Kaitong Hu, Anna Kazeykina, Zhenjie Ren. Mean-field Langevin System, Optimal Control and Deep Neural Networks. 2019. ⟨hal-02291488⟩
123 Consultations
151 Téléchargements

Partager

Gmail Facebook X LinkedIn More