English

Three algorithms for solving high-dimensional fully-coupled FBSDEs through deep learning

Numerical Analysis 2020-02-04 v4 Machine Learning Numerical Analysis Probability

Abstract

Recently, the deep learning method has been used for solving forward-backward stochastic differential equations (FBSDEs) and parabolic partial differential equations (PDEs). It has good accuracy and performance for high-dimensional problems. In this paper, we mainly solve fully coupled FBSDEs through deep learning and provide three algorithms. Several numerical results show remarkable performance especially for high-dimensional cases.

Keywords

Cite

@article{arxiv.1907.05327,
  title  = {Three algorithms for solving high-dimensional fully-coupled FBSDEs through deep learning},
  author = {Shaolin Ji and Shige Peng and Ying Peng and Xichuan Zhang},
  journal= {arXiv preprint arXiv:1907.05327},
  year   = {2020}
}

Comments

24 pages, 7 figures

R2 v1 2026-06-23T10:18:44.670Z