Convergence of the Deep BSDE method for FBSDEs with non-Lipschitz coefficients  

作　　者：Yifan Jiang Jinfeng Li 

机构地区：[1]Mathematical Institute,University of Oxford,Oxford OX26GG,United Kingdom [2]School of Mathematical Sciences,Fudan University,Shanghai 200433,China

出　　处：《Probability, Uncertainty and Quantitative Risk》2021年第4期391-408,共18页概率、不确定性与定量风险（英文）

基　　金：the EPSRC Centre for Doctoral Training in Mathematics of Random Systems:Analysis,Modelling,and Simulation(Grant No.EP/S023925/1).

摘　　要：This paper is dedicated to solving high-dimensional coupled FBSDEs with non- Lipschitz diffusion coefficients numerically. Under mild conditions, we provided a posterior estimate of the numerical solution that holds for any time duration. This posterior estimate validates the convergence of the recently proposed Deep BSDE method. In addition, we developed a numerical scheme based on the Deep BSDE method and presented numerical examples in financial markets to demonstrate the high performance.

关 键 词：Forward-backward SDEs Deep neural networks Stochastic control 

分 类 号：O17[理学—数学]