Deep backward schemes for high-dimensional nonlinear PDEs - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Mathematics of Computation Année : 2020

Deep backward schemes for high-dimensional nonlinear PDEs

Résumé

We propose new machine learning schemes for solving high dimensional nonlinear partial differential equations (PDEs). Relying on the classical backward stochastic differential equation (BSDE) representation of PDEs, our algorithms estimate simultaneously the solution and its gradient by deep neural networks. These approximations are performed at each time step from the minimization of loss functions defined recursively by backward induction. The methodology is extended to variational inequalities arising in optimal stopping problems. We analyze the convergence of the deep learning schemes and provide error estimates in terms of the universal approximation of neural networks. Numerical results show that our algorithms give very good results till dimension 50 (and certainly above), for both PDEs and variational inequalities problems. For the PDEs resolution, our results are very similar to those obtained by the recent method in \cite{weinan2017deep} when the latter converges to the right solution or does not diverge. Numerical tests indicate that the proposed methods are not stuck in poor local minima as it can be the case with the algorithm designed in \cite{weinan2017deep}, and no divergence is experienced. The only limitation seems to be due to the inability of the considered deep neural networks to represent a solution with a too complex structure in high dimension.
Fichier principal
Vignette du fichier
MLBSDE-HPW-finalMC.pdf (1.09 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02005362 , version 1 (04-02-2019)
hal-02005362 , version 2 (04-06-2020)

Identifiants

Citer

Côme Huré, Huyên Pham, Xavier Warin. Deep backward schemes for high-dimensional nonlinear PDEs. Mathematics of Computation, 2020, 89 (324), pp.1547-1579. ⟨10.1090/mcom/3514⟩. ⟨hal-02005362v2⟩
561 Consultations
1595 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More