Deep learning algorithms for solving high-dimensional nonlinear backward stochastic differential equations

DOI10.3934/DCDSB.2023151OpenAlexW3089807094MaRDI QIDQ6201366FDOQ6201366

Authors: Lorenc Kapllani, Long Teng 

Publication date: 20 February 2024

Published in: Discrete and Continuous Dynamical Systems. Series B (Search for Journal in Brave)

Abstract: In this work, we propose a new deep learning-based scheme for solving high dimensional nonlinear backward stochastic differential equations (BSDEs). The idea is to reformulate the problem as a global optimization, where the local loss functions are included. Essentially, we approximate the unknown solution of a BSDE using a deep neural network and its gradient with automatic differentiation. The approximations are performed by globally minimizing the quadratic local loss function defined at each time step, which always includes the terminal condition. This kind of loss functions are obtained by iterating the Euler discretization of the time integrals with the terminal condition. Our formulation can prompt the stochastic gradient descent algorithm not only to take the accuracy at each time layer into account, but also converge to a good local minima. In order to demonstrate performances of our algorithm, several high-dimensional nonlinear BSDEs including pricing problems in finance are provided.

Full work available at URL: https://arxiv.org/abs/2010.01319

Recommendations

• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Control variate method for deep BSDE solver using weak approximation
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Deep backward schemes for high-dimensional nonlinear PDEs
• A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for deep BSDE solver

zbMATH Keywords

high-dimensional problemsbackward stochastic differential equationsrecurrent neural networkautomatic differentiationdeep neural networknonlinear option pricingadditive discretization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Probabilistic models, generic numerical methods in probability and statistics (65C20) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical solutions to stochastic differential and integral equations (65C30)

Cites Work

• Title not available (Why is that?)
• A Fourier cosine method for an efficient computation of solutions to BSDEs
• A New Kind of Accurate Numerical Method for Backward Stochastic Differential Equations
• A Stable Multistep Scheme for Solving Backward Stochastic Differential Equations
• A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for deep BSDE solver
• A numerical scheme for BSDEs
• A parallel algorithm for solving BSDEs
• A probabilistic numerical method for fully nonlinear parabolic PDEs
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• A regression-based Monte Carlo method to solve backward stochastic differential equations
• A sparse-grid method for multi-dimensional backward stochastic differential equations
• Adapted solution of a backward stochastic differential equation
• Approximation error analysis of some deep backward schemes for nonlinear PDEs
• Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
• Backward Stochastic Differential Equations in Finance
• Backward stochastic differential equations with enlarged filtration: Option hedging of an insider trader in a financial market with jumps
• CREDIT RISK PREMIA AND QUADRATIC BSDEs WITH A SINGLE JUMP
• Convergence of a Robust Deep FBSDE Method for Stochastic Control
• Convergence of the deep BSDE method for FBSDEs with non-Lipschitz coefficients
• Convergence of the deep BSDE method for coupled FBSDEs
• Deep backward schemes for high-dimensional nonlinear PDEs
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Deep neural network framework based on backward stochastic differential equations for pricing and hedging American options in high dimensions
• Deep splitting method for parabolic PDEs
• Deep xVA Solver: A Neural Network–Based Counterparty Credit Risk Management Framework
• Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
• Efficient spectral sparse grid approximations for solving multi-dimensional forward backward sdes
• Gradient boosting-based numerical methods for high-dimensional backward stochastic differential equations
• Learning representations by back-propagating errors
• Linear regression MDP scheme for discrete backward stochastic differential equations under general conditions
• Machine learning for semi linear PDEs
• Multilayer feedforward networks are universal approximators
• Multilevel Picard approximations of high-dimensional semilinear partial differential equations with locally monotone coefficient functions
• Multilevel Picard iterations for solving smooth semilinear parabolic heat equations
• Multistep schemes for solving backward stochastic differential equations on GPU
• Neural networks-based backward scheme for fully nonlinear PDEs
• New kinds of high-order multistep schemes for coupled forward backward stochastic differential equations
• Numerical Fourier method and second-order Taylor scheme for backward SDEs in finance
• Numerical simulations for full history recursive multilevel Picard approximations for systems of high-dimensional partial differential equations
• On Numerical Approximations of Forward-Backward Stochastic Differential Equations
• On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations
• Overcoming the curse of dimensionality in the numerical approximation of backward stochastic differential equations
• Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
• Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
• Rate of convergence of an empirical regression method for solving generalized backward stochastic differential equations
• Solving BSDE with Adaptive Control Variate
• Solving Backward Stochastic Differential Equations Using the Cubature Method: Application to Nonlinear Pricing
• Solving high-dimensional partial differential equations using deep learning
• Stochastic differential equations. An introduction with applications.
• Stratified regression Monte-Carlo scheme for semilinear PDEs and BSDEs with large scale parallelization on GPUs
• Time discretization and Markovian iteration for coupled FBSDEs

Cited In (4)

• The Effect of the Number of Neural Networks on Deep Learning Schemes for Solving High Dimensional Nonlinear Backward Stochastic Differential Equations
• Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems
• Deep learning scheme for forward utilities using ergodic BSDEs
• A deep-genetic algorithm (deep-GA) approach for high-dimensional nonlinear parabolic partial differential equations

This page was built for publication: Deep learning algorithms for solving high-dimensional nonlinear backward stochastic differential equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6201366)