Convergence of the deep BSDE method for coupled FBSDEs

DOI10.1186/s41546-020-00047-wzbMath1454.60105arXiv1811.01165OpenAlexW2899507754MaRDI QIDQ2223111

Jihao Long, Jiequn Han

Publication date: 28 January 2021

Published in: Probability, Uncertainty and Quantitative Risk (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.01165

zbMATH Keywords

numericshigh dimensiondeep learningforward-backward SDEweakly coupled condition

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical solutions to stochastic differential and integral equations (65C30)

Related Items (41)

Numerical approximations of coupled forward–backward SPDEs ⋮ Convergence of a Robust Deep FBSDE Method for Stochastic Control ⋮ A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for deep BSDE solver ⋮ Deep learning for constrained utility maximisation ⋮ Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms ⋮ Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities ⋮ Numerical approximation of singular forward-backward SDEs ⋮ Convergence of deep fictitious play for stochastic differential games ⋮ Unbiased Deep Solvers for Linear Parametric PDEs ⋮ Convergence of the deep BSDE method for FBSDEs with non-Lipschitz coefficients ⋮ Solving stochastic optimal control problem via stochastic maximum principle with deep learning method ⋮ Control variate method for deep BSDE solver using weak approximation ⋮ Asset pricing with general transaction costs: Theory and numerics ⋮ Neural networks for first order HJB equations and application to front propagation with obstacle terms ⋮ Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes ⋮ Numerical resolution of McKean-Vlasov FBSDEs using neural networks ⋮ Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning ⋮ Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems ⋮ Numerical methods for backward stochastic differential equations: a survey ⋮ Deep xVA Solver: A Neural Network–Based Counterparty Credit Risk Management Framework ⋮ Deep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov Equations ⋮ Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing ⋮ Learning High-Dimensional McKean–Vlasov Forward-Backward Stochastic Differential Equations with General Distribution Dependence ⋮ Deep learning algorithms for solving high-dimensional nonlinear backward stochastic differential equations ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ Unnamed Item ⋮ A modified MSA for stochastic control problems ⋮ Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis ⋮ Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations ⋮ High-order combined multi-step scheme for solving forward backward stochastic differential equations ⋮ A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains ⋮ Deep Splitting Method for Parabolic PDEs ⋮ Deep backward schemes for high-dimensional nonlinear PDEs ⋮ Gradient convergence of deep learning-based numerical methods for BSDEs ⋮ Reinforcement learning and stochastic optimisation ⋮ Algorithms of data generation for deep learning and feedback design: a survey ⋮ FBSDE based neural network algorithms for high-dimensional quasilinear parabolic PDEs ⋮ Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning ⋮ Approximation Error Analysis of Some Deep Backward Schemes for Nonlinear PDEs ⋮ Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks ⋮ Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. II: The finite horizon case

Uses Software

• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Efficient numerical Fourier methods for coupled forward-backward SDEs
• Forward-backward stochastic differential equations and quasilinear parabolic PDEs
• Backward-forward stochastic differential equations
• Solving forward-backward stochastic differential equations explicitly -- a four step scheme
• A numerical scheme for BSDEs
• Multilayer feedforward networks are universal approximators
• Branching diffusion representation of semilinear PDEs and Monte Carlo approximation
• On the Malliavin approach to Monte Carlo approximation of conditional expectations
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Time discretization and Markovian iteration for coupled FBSDEs
• Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
• Deep vs. shallow networks: An approximation theory perspective
• Least-Squares Monte Carlo for Backward SDEs
• Universal approximation bounds for superpositions of a sigmoidal function
• Solving high-dimensional partial differential equations using deep learning
• Numerical Algorithms for Forward-Backward Stochastic Differential Equations
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Convergence of the deep BSDE method for coupled FBSDEs