Convergence of the Deep BSDE Method for Coupled FBSDEs

Abstract

The recently proposed numerical algorithm, deep BSDE method, has shown remarkable performance in solving high-dimensional forward-backward stochastic differential equations (FBSDEs) and parabolic partial differential equations (PDEs). This article lays a theoretical foundation for the deep BSDE method in the general case of coupled FBSDEs. In particular, a posteriori error estimation of the solution is provided and it is proved that the error converges to zero given the universal approximation capability of neural networks. Numerical results are presented to demonstrate the accuracy of the analyzed algorithm in solving high-dimensional coupled FBSDEs.

References in corpus (8)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• Why Deep Neural Networks for Function Approximation?
• Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations
• Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• Time discretization and Markovian iteration for coupled FBSDEs
• Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games

Cited by in corpus (45)

• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• Deep splitting method for parabolic PDEs
• Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
• An overview on deep learning-based approximation methods for partial differential equations
• Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
• Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks
• Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
• Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
• Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations
• Numerical simulations for full history recursive multilevel Picard approximations for systems of high-dimensional partial differential equations
• Numerical methods for backward stochastic differential equations: A survey
• Uniform error estimates for artificial neural network approximations for heat equations
• Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
• Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games
• A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for Deep BSDE solver
• Convergence of the Deep BSDE method for FBSDEs with non-Lipschitz coefficients
• Neural networks-based algorithms for stochastic control and PDEs in finance
• Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
• Deep neural network approximations for Monte Carlo algorithms
• Algorithms of Data Development For Deep Learning and Feedback Design
• A neural network based policy iteration algorithm with global $H^2$-superlinear convergence for stochastic games on domains
• Generalised multilevel Picard approximations
• Convergence of Deep Fictitious Play for Stochastic Differential Games
• Deep backward schemes for high-dimensional nonlinear PDEs
• Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
• A Priori Analysis of Stable Neural Network Solutions to Numerical PDEs
• Multilevel Picard approximations for high-dimensional semilinear second-order PDEs with Lipschitz nonlinearities
• Reproducing Activation Function for Deep Learning
• Deep learning algorithms for solving high dimensional nonlinear backward stochastic differential equations
• Deep Fictitious Play for Stochastic Differential Games
• A posteriori error estimates for fully coupled McKean-Vlasov forward-backward SDEs
• Solving PDEs on Unknown Manifolds with Machine Learning
• Unbiased deep solvers for linear parametric PDEs
• Three algorithms for solving high-dimensional fully-coupled FBSDEs through deep learning
• Relative wealth concerns with partial information and heterogeneous priors
• Deep Learning for Mean Field Games and Mean Field Control with Applications to Finance
• Numerical approximation of singular Forward-Backward SDEs
• Density Propagation with Characteristics-based Deep Learning
• A learning scheme by sparse grids and Picard approximations for semilinear parabolic PDEs
• Large-Scale Multi-Agent Deep FBSDEs
• Deep Learning for Constrained Utility Maximisation
• On the space-time expressivity of ResNets
• XNet-Enhanced Deep BSDE Method and Numerical Analysis
• Solving stochastic optimal control problem via stochastic maximum principle with deep learning method
• Deep Operator BSDE: a Numerical Scheme to Approximate Solution Operators