Deep Forward-Backward Dynamic Programming Schemes for High-Dimensional Semilinear Nonlocal PDEs and FBSDE with Jumps

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Wansheng, Pan, Jiangtao, Wang, Jie, Ye, Zaijun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912672149143552
author Wang, Wansheng
Pan, Jiangtao
Wang, Jie
Ye, Zaijun
author_facet Wang, Wansheng
Pan, Jiangtao
Wang, Jie
Ye, Zaijun
contents We propose a new deep learning algorithm for solving high-dimensional parabolic integro-differential equations (PIDEs) and forward-backward stochastic differential equations with jumps (FBSDEJs). This novel algorithm can be viewed as an extension and generalization of the DBDP2 scheme and a dynamic programming version of the forward-backward algorithm proposed recently for high-dimensional semilinear PDEs and semilinear PIDEs, respectively. Different from the DBDP2 scheme for semilinear PDEs, our algorithm approximate simultaneously the solution and the integral kernel by deep neural networks, while the gradient of the solution is approximated by numerical differential techniques. The related error estimates for the integral kernel approximation play key roles in deriving error estimates for the novel algorithm. Numerical experiments confirm our theoretical results and verify the effectiveness of the proposed methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23091
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Forward-Backward Dynamic Programming Schemes for High-Dimensional Semilinear Nonlocal PDEs and FBSDE with Jumps
Wang, Wansheng
Pan, Jiangtao
Wang, Jie
Ye, Zaijun
Numerical Analysis
60H35, 65C20, 65M15, 65C30, 60H10, 65M75
We propose a new deep learning algorithm for solving high-dimensional parabolic integro-differential equations (PIDEs) and forward-backward stochastic differential equations with jumps (FBSDEJs). This novel algorithm can be viewed as an extension and generalization of the DBDP2 scheme and a dynamic programming version of the forward-backward algorithm proposed recently for high-dimensional semilinear PDEs and semilinear PIDEs, respectively. Different from the DBDP2 scheme for semilinear PDEs, our algorithm approximate simultaneously the solution and the integral kernel by deep neural networks, while the gradient of the solution is approximated by numerical differential techniques. The related error estimates for the integral kernel approximation play key roles in deriving error estimates for the novel algorithm. Numerical experiments confirm our theoretical results and verify the effectiveness of the proposed methods.
title Deep Forward-Backward Dynamic Programming Schemes for High-Dimensional Semilinear Nonlocal PDEs and FBSDE with Jumps
topic Numerical Analysis
60H35, 65C20, 65M15, 65C30, 60H10, 65M75
url https://arxiv.org/abs/2510.23091