PreprintarXiv licencearXiv
A Deep BSDE Method for a Class of Strongly Coupled FBSDEs
Abstract
We investigate a variant of the deep BSDE method introduced by E et al. (2017, 2018). The key novelty is that we establish an a-posteriori convergence result for the approximation of strongly coupled forward-backward stochastic differential equations (FBSDEs), i.e., our result holds without any assumptions on small time horizons, monotonicity or weak coupling that are typically imposed in the literature on the deep BSDE method. Instead, we rely on smoothness assumptions on the coefficients and cover FBSDEs in which the coupling of the BSDE into the SDE depends on both the backward component Y and the control component Z. Numerical experiments illustrate the theoretical results and demonstrate the applicability of the proposed approach.
Related
- Deep Truncated FBSDE Method for High-Dimensional Nonlinear PDEs and Fully Coupled FBSDEs
- A fast risk assessment method for power balance under extreme weather conditions based on deep reinforcement learning with a coupled attention mechanism
- Strongly linearly convex exhaustion of a class of ℂ-convex domains
- Vertex-transitive strongly regular graphs in the switching class of doubly transitive two-graphs
- Four class association scheme double covers of strongly regular graphs
BibTeX
@misc{bender2026deep,
title = {{A Deep BSDE Method for a Class of Strongly Coupled FBSDEs}},
author = {Christian Bender and Benedikt Simon Flierl},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.29285},
eprint = {2609.29285},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.29285},
}
RIS
TY - UNPB
TI - A Deep BSDE Method for a Class of Strongly Coupled FBSDEs
AU - Christian Bender
AU - Benedikt Simon Flierl
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.29285
UR - https://arxiv.org/abs/2609.29285
AB - We investigate a variant of the deep BSDE method introduced by E et al. (2017, 2018). The key novelty is that we establish an a-posteriori convergence result for the approximation of strongly coupled forward-backward stochastic differential equations (FBSDEs), i.e., our result holds without any assumptions on small time horizons, monotonicity or weak coupling that are typically imposed in the literature on the deep BSDE method. Instead, we rely on smoothness assumptions on the coefficients and cover FBSDEs in which the coupling of the BSDE into the SDE depends on both the backward component Y and the control component Z. Numerical experiments illustrate the theoretical results and demonstrate the applicability of the proposed approach.
ER -