Langevin algorithms for Markovian Neural Networks and Deep Stochastic control - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Langevin algorithms for Markovian Neural Networks and Deep Stochastic control

Résumé

Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we study the possibilities of training acceleration for the numerical resolution of stochastic control problems through gradient descent, where the control is parametrized by a neural network. If the control is applied at many discretization times then solving the stochastic control problem reduces to minimizing the loss of a very deep neural network. We numerically show that Langevin algorithms improve the training on various stochastic control problems like hedging and resource management, and for different choices of gradient descent methods.
Fichier principal
Vignette du fichier
2212.12018.pdf (470.97 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03980632 , version 1 (09-02-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-03980632 , version 1

Citer

Pierre Bras, Gilles Pagès. Langevin algorithms for Markovian Neural Networks and Deep Stochastic control. 2022. ⟨hal-03980632⟩
9 Consultations
38 Téléchargements

Partager

Gmail Facebook X LinkedIn More