Gradient convergence of deep learning-based numerical methods for BSDEs

DOI10.1007/s11401-021-0253-xzbMath1470.62126OpenAlexW3143755246MaRDI QIDQ2044106

Shanjian Tang, Zi Xuan Wang

Publication date: 4 August 2021

Published in: Chinese Annals of Mathematics. Series B (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11401-021-0253-x

zbMATH Keywords

convergence resultPDEsBSDEsdeep learningnonconvex stochastic programming

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20)

Related Items (1)

Unbiased Deep Solvers for Linear Parametric PDEs

Uses Software

• DGM

Cites Work

• Unnamed Item
• Unnamed Item
• Numerical Fourier method and second-order Taylor scheme for backward SDEs in finance
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• The steepest descent method for forward-backward SDEs
• Numerical solution for high order differential equations using a hybrid neural network-optimization method
• Efficient numerical Fourier methods for coupled forward-backward SDEs
• Forward-backward stochastic differential equations and quasilinear parabolic PDEs
• A globally convergent algorithm for nonconvex optimization based on block coordinate update
• DGM: a deep learning algorithm for solving partial differential equations
• Gradient descent optimizes over-parameterized deep ReLU networks
• Convergence of the deep BSDE method for coupled FBSDEs
• A proposal on machine learning via dynamical systems
• Time discretization and Markovian iteration for coupled FBSDEs
• Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
• A forward-backward stochastic algorithm for quasi-linear PDEs
• Numerical methods for forward-backward stochastic differential equations
• On Numerical Approximations of Forward-Backward Stochastic Differential Equations
• Robust Stochastic Approximation Approach to Stochastic Programming
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming

This page was built for publication: Gradient convergence of deep learning-based numerical methods for BSDEs