The deep multi-FBSDE method: a robust deep learning method for coupled FBSDEs
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910977238237184 |
|---|---|
| author | Andersson, Kristoffer Andersson, Adam Oosterlee, Cornelis W. |
| author_facet | Andersson, Kristoffer Andersson, Adam Oosterlee, Cornelis W. |
| contents | We introduce the deep multi-FBSDE method for robust approximation of coupled forward-backward stochastic differential equations (FBSDEs), focusing on cases where the deep BSDE method of Han, Jentzen, and E (2018) fails to converge. To overcome the convergence issues, we consider a family of FBSDEs that are equivalent to the original problem in the sense that they satisfy the same associated partial differential equation (PDE). Our algorithm proceeds in two phases: first, we approximate the initial condition for the FBSDE family, and second, we approximate the original FBSDE using the initial condition approximated in the first phase. Numerical experiments show that our method converges even when the standard deep BSDE method does not. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13193 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The deep multi-FBSDE method: a robust deep learning method for coupled FBSDEs Andersson, Kristoffer Andersson, Adam Oosterlee, Cornelis W. Numerical Analysis Optimization and Control Computational Finance 60H35, 68T07, 35K58, 93E20 We introduce the deep multi-FBSDE method for robust approximation of coupled forward-backward stochastic differential equations (FBSDEs), focusing on cases where the deep BSDE method of Han, Jentzen, and E (2018) fails to converge. To overcome the convergence issues, we consider a family of FBSDEs that are equivalent to the original problem in the sense that they satisfy the same associated partial differential equation (PDE). Our algorithm proceeds in two phases: first, we approximate the initial condition for the FBSDE family, and second, we approximate the original FBSDE using the initial condition approximated in the first phase. Numerical experiments show that our method converges even when the standard deep BSDE method does not. |
| title | The deep multi-FBSDE method: a robust deep learning method for coupled FBSDEs |
| topic | Numerical Analysis Optimization and Control Computational Finance 60H35, 68T07, 35K58, 93E20 |
| url | https://arxiv.org/abs/2503.13193 |