Deep backward schemes for high-dimensional nonlinear PDEs

DOI10.1090/mcom/3514zbMath1440.60063arXiv1902.01599OpenAlexW2993551995WikidataQ114094322 ScholiaQ114094322MaRDI QIDQ4960067

Xavier Warin, Côme Huré, Huyên Pham

Publication date: 8 April 2020

Published in: Mathematics of Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1902.01599

zbMATH Keywords

backward stochastic differential equationsoptimal stopping problemdeep neural networksnonlinear PDEs in high dimension

Mathematics Subject Classification ID

Probabilistic models, generic numerical methods in probability and statistics (65C20) Stability and convergence of numerical methods for initial value and initial-boundary value problems involving PDEs (65M12) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35)

Related Items (69)

Numerical approximations of coupled forward–backward SPDEs ⋮ Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space ⋮ Convergence of a Robust Deep FBSDE Method for Stochastic Control ⋮ APFOS-Net: asymptotic preserving scheme for anisotropic elliptic equations with deep neural network ⋮ Higher-order deep solver of non-linear PDEs implied by a non-linear discrete Clark-Ocone formula ⋮ Learning a functional control for high-frequency finance ⋮ On quadrature rules for solving partial differential equations using neural networks ⋮ Gradient boosting-based numerical methods for high-dimensional backward stochastic differential equations ⋮ SympOCnet: Solving Optimal Control Problems with Applications to High-Dimensional Multiagent Path Planning Problems ⋮ Extensions of the deep Galerkin method ⋮ DeepSets and their derivative networks for solving symmetric PDEs ⋮ Pricing Options under Rough Volatility with Backward SPDEs ⋮ Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms ⋮ The deep parametric PDE method and applications to option pricing ⋮ Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities ⋮ Multilevel Picard approximations of high-dimensional semilinear partial differential equations with locally monotone coefficient functions ⋮ Numerical approximation of singular forward-backward SDEs ⋮ Deep neural networks based temporal-difference methods for high-dimensional parabolic partial differential equations ⋮ Convergence of deep fictitious play for stochastic differential games ⋮ An efficient weak Euler-Maruyama type approximation scheme of very high dimensional SDEs by orthogonal random variables ⋮ Unbiased Deep Solvers for Linear Parametric PDEs ⋮ Solving stochastic optimal control problem via stochastic maximum principle with deep learning method ⋮ A Neural Network Approach to High-Dimensional Optimal Switching Problems with Jumps in Energy Markets ⋮ Deep learning methods for partial differential equations and related parameter identification problems ⋮ Numerical solution of the modified and non-Newtonian Burgers equations by stochastic coded trees ⋮ Pathwise CVA regressions with oversimulated defaults ⋮ 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 ⋮ The Kolmogorov infinite dimensional equation in a Hilbert space via deep learning methods ⋮ A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations ⋮ Numerical resolution of McKean-Vlasov FBSDEs using neural networks ⋮ Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems ⋮ Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems ⋮ Numerical methods for backward stochastic differential equations: a survey ⋮ Efficient pricing and hedging of high-dimensional American options using deep recurrent networks ⋮ Deep xVA Solver: A Neural Network–Based Counterparty Credit Risk Management Framework ⋮ Deep Curve-Dependent PDEs for Affine Rough Volatility ⋮ Stability of backward stochastic differential equations: the general Lipschitz case ⋮ Deep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov Equations ⋮ Solving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculus ⋮ A level-set approach for stochastic optimal control problems under controlled-loss constraints ⋮ 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 ⋮ A fully nonlinear Feynman-Kac formula with derivatives of arbitrary orders ⋮ Neural Control of Parametric Solutions for High-Dimensional Evolution PDEs ⋮ A deep branching solver for fully nonlinear partial differential equations ⋮ Deep learning algorithms for solving high-dimensional nonlinear backward stochastic differential equations ⋮ Deep learning approximations for non-local nonlinear PDEs with Neumann boundary conditions ⋮ Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems ⋮ Unnamed Item ⋮ Neural networks-based backward scheme for fully nonlinear PDEs ⋮ Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations ⋮ Discretization and machine learning approximation of BSDEs with a constraint on the gains-process ⋮ Deep Splitting Method for Parabolic PDEs ⋮ Computing Lyapunov functions using deep neural networks ⋮ Reinforcement learning and stochastic optimisation ⋮ Tensor Decomposition Methods for High-dimensional Hamilton--Jacobi--Bellman Equations ⋮ Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures ⋮ An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations ⋮ Deep combinatorial optimisation for optimal stopping time problems: application to swing options pricing. ⋮ Deep learning schemes for parabolic nonlocal integro-differential equations ⋮ Deep neural network framework based on backward stochastic differential equations for pricing and hedging American options in high dimensions ⋮ XVA analysis from the balance sheet ⋮ Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning ⋮ McKean Feynman-Kac probabilistic representations of non-linear partial differential equations ⋮ Approximation Error Analysis of Some Deep Backward Schemes for Nonlinear PDEs ⋮ Approximate value adjustments for European claims

Uses Software

• DGM

Cites Work

• Adapted solution of a backward stochastic differential equation
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Variational inequalities and the pricing of American options
• Rate of convergence of an empirical regression method for solving generalized backward stochastic differential equations
• On irregular functionals of SDEs and the Euler scheme
• Reflected solutions of backward SDE's, and related obstacle problems for PDE's
• A numerical scheme for BSDEs
• Multilayer feedforward networks are universal approximators
• Nesting Monte Carlo for high-dimensional non-linear PDEs
• Branching diffusion representation of semilinear PDEs and Monte Carlo approximation
• DGM: a deep learning algorithm for solving partial differential equations
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• Convergence of the deep BSDE method for coupled FBSDEs
• On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations
• Machine learning for semi linear PDEs
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
• Discrete-time approximation for continuously and discretely reflected BSDEs
• A regression-based Monte Carlo method to solve backward stochastic differential equations
• Error analysis of the optimal quantization algorithm for obstacle problems.
• Monte-Carlo Valuation of American Options: Facts and New Algorithms to Improve Existing Methods
• Solving high-dimensional partial differential equations using deep learning
• Deep optimal stopping
• Unnamed Item

This page was built for publication: Deep backward schemes for high-dimensional nonlinear PDEs