Neural networks-based backward scheme for fully nonlinear PDEs - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue SN Partial Differential Equations and Applications Année : 2021

Neural networks-based backward scheme for fully nonlinear PDEs

Résumé

We propose a numerical method for solving high dimensional fully nonlinear partial differential equations (PDEs). Our algorithm estimates simultaneously by backward time induction the solution and its gradient by multi-layer neural networks, while the Hessian is approximated by automatic differentiation of the gradient at previous step. This methodology extends to the fully nonlinear case the approach recently proposed in \cite{HPW19} for semi-linear PDEs. Numerical tests illustrate the performance and accuracy of our method on several examples in high dimension with nonlinearity on the Hessian term including a linear quadratic control problem with control on the diffusion coefficient, Monge-Ampère equation and Hamilton-Jacobi-Bellman equation in portfolio optimization.
Fichier principal
Vignette du fichier
FullNonLin-rev2.pdf (1.51 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02196165 , version 1 (30-07-2019)
hal-02196165 , version 2 (28-05-2020)
hal-02196165 , version 3 (10-12-2020)

Identifiants

Citer

Huyen Pham, Xavier Warin, Maximilien Germain. Neural networks-based backward scheme for fully nonlinear PDEs. SN Partial Differential Equations and Applications, 2021, 2, ⟨10.1007/s42985-020-00062-8⟩. ⟨hal-02196165v3⟩
763 Consultations
357 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More