Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations

DOI10.1007/s40304-017-0117-6zbMath1382.65016arXiv1706.04702OpenAlexW2625995436MaRDI QIDQ681281

Jiequn Han, E. Weinan, Arnulf Jentzen

Publication date: 30 January 2018

Published in: Communications in Mathematics and Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1706.04702

zbMATH Keywords

control Hamilton-Jacobi-Bellman equation backward stochastic differential equations Allen-Cahn equation numerical result deep learning Feynman-Kac nonlinear pricing model

Mathematics Subject Classification ID

PDEs in connection with fluid mechanics (35Q35) Stochastic partial differential equations (aspects of stochastic analysis) (60H15) PDEs with randomness, stochastic partial differential equations (35R60) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical solutions to stochastic differential and integral equations (65C30) Hamilton-Jacobi equations (35F21) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75)

Related Items (only showing first 100 items - show all)

Numerical approximations of coupled forward–backward SPDEs ⋮ 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 ⋮ Deep Adaptive Basis Galerkin Method for High-Dimensional Evolution Equations With Oscillatory Solutions ⋮ A Regularity Theory for Static Schrödinger Equations on \(\boldsymbol{\mathbb{R}}\)^d in Spectral Barron Spaces ⋮ Convergence of Physics-Informed Neural Networks Applied to Linear Second-Order Elliptic Interface Problems ⋮ A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations ⋮ 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 ⋮ An Augmented Lagrangian Deep Learning Method for Variational Problems with Essential Boundary Conditions ⋮ A Deep Learning Method for Elliptic Hemivariational Inequalities ⋮ Deep Unfitted Nitsche Method for Elliptic Interface Problems ⋮ Physics Informed Neural Networks (PINNs) For Approximating Nonlinear Dispersive PDEs ⋮ A hybrid deep learning method for optimal insurance strategies: algorithms and convergence analysis ⋮ Approximating Optimal feedback Controllers of Finite Horizon Control Problems Using Hierarchical Tensor Formats ⋮ Neural Parametric Fokker--Planck Equation ⋮ An efficient weak Euler-Maruyama type approximation scheme of very high dimensional SDEs by orthogonal random variables ⋮ Unbiased Deep Solvers for Linear Parametric PDEs ⋮ Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications ⋮ Adaptive deep neural networks methods for high-dimensional partial differential equations ⋮ Convergence of the deep BSDE method for FBSDEs with non-Lipschitz coefficients ⋮ DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method ⋮ Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification ⋮ Numerical computation of probabilities for nonlinear SDEs in high dimension using Kolmogorov equation ⋮ Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning ⋮ Data-driven hedging of stock index options via deep learning ⋮ Solving stochastic optimal control problem via stochastic maximum principle with deep learning method ⋮ Stochastic viscosity approximations of Hamilton–Jacobi equations and variance reduction ⋮ Simultaneous neural network approximation for smooth functions ⋮ Splitting scheme for backward doubly stochastic differential equations ⋮ Control variate method for deep BSDE solver using weak approximation ⋮ On the approximation of functions by tanh neural networks ⋮ Randomized neural network with Petrov-Galerkin methods for solving linear and nonlinear partial differential equations ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Artificial neural networks for solving elliptic differential equations with boundary layer ⋮ Numerical solution of the modified and non-Newtonian Burgers equations by stochastic coded trees ⋮ PI-VAE: physics-informed variational auto-encoder for stochastic differential equations ⋮ Solving nonconvex energy minimization problems in martensitic phase transitions with a mesh-free deep learning approach ⋮ Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes ⋮ The Random Feature Method for Time-Dependent Problems ⋮ MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs ⋮ The Effect of the Number of Neural Networks on Deep Learning Schemes for Solving High Dimensional Nonlinear Backward Stochastic Differential Equations ⋮ Deep Ritz method with adaptive quadrature for linear elasticity ⋮ Inverse stochastic optimal controls ⋮ Learning high frequency data via the coupled frequency predictor-corrector triangular DNN ⋮ Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation ⋮ CPINNs: a coupled physics-informed neural networks for the closed-loop geothermal system ⋮ Active learning based sampling for high-dimensional nonlinear partial differential equations ⋮ Space-time error estimates for deep neural network approximations for differential equations ⋮ Neural network architectures using min-plus algebra for solving certain high-dimensional optimal control problems and Hamilton-Jacobi PDEs ⋮ Solving Dirichlet boundary problems for ODEs via swarm intelligence ⋮ Mini-workshop: Analysis of data-driven optimal control. Abstracts from the mini-workshop held May 9--15, 2021 (hybrid meeting) ⋮ Stochastic Methods for Solving High-Dimensional Partial Differential Equations ⋮ Overcoming the curse of dimensionality in the numerical approximation of backward stochastic differential equations ⋮ OPTIMAL INSURANCE STRATEGIES: A HYBRID DEEP LEARNING MARKOV CHAIN APPROXIMATION APPROACH ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ Neural network-based variational methods for solving quadratic porous medium equations in high dimensions ⋮ BI-GreenNet: learning Green's functions by boundary integral network ⋮ A Unified Probabilistic Discretization Scheme for FBSDEs: Stability, Consistency, and Convergence Analysis ⋮ Unnamed Item ⋮ Error bounds for approximations with deep ReLU neural networks in Ws,p norms ⋮ Numerical solution of inverse problems by weak adversarial networks ⋮ Optimizing a portfolio of mean-reverting assets with transaction costs via a feedforward neural network ⋮ Accelerated share repurchase and other buyback programs: what neural networks can bring ⋮ Unnamed Item ⋮ Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis ⋮ A finite element approximation of a current-induced magnetization dynamics model ⋮ Approximate Optimal Controls via Instanton Expansion for Low Temperature Free Energy Computation ⋮ Unnamed Item ⋮ Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations ⋮ Machine Learning and Computational Mathematics ⋮ Finite Neuron Method and Convergence Analysis ⋮ Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks ⋮ Deep Network Approximation Characterized by Number of Neurons ⋮ Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks ⋮ Multi-Scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains ⋮ Numerical Simulations for Full History Recursive Multilevel Picard Approximations for Systems of High-Dimensional Partial Differential Equations ⋮ Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions ⋮ Unnamed Item ⋮ Path-Dependent Deep Galerkin Method: A Neural Network Approach to Solve Path-Dependent Partial Differential Equations ⋮ Deep Splitting Method for Parabolic PDEs ⋮ Deep backward schemes for high-dimensional nonlinear PDEs ⋮ Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations ⋮ A Multiscale Neural Network Based on Hierarchical Matrices ⋮ Variational approach to rare event simulation using least-squares regression ⋮ Solving inverse problems using data-driven models ⋮ Jets and differential linear logic ⋮ Machine learning for pricing American options in high-dimensional Markovian and non-Markovian models ⋮ Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games I: The Ergodic Case ⋮ Tensor Decomposition Methods for High-dimensional Hamilton--Jacobi--Bellman Equations ⋮ The Gap between Theory and Practice in Function Approximation with Deep Neural Networks ⋮ Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences ⋮ Using machine learning to predict extreme events in complex systems ⋮ Deep neural network framework based on backward stochastic differential equations for pricing and hedging American options in high dimensions ⋮ A multi-level procedure for enhancing accuracy of machine learning algorithms ⋮ Solving high-dimensional optimal stopping problems using deep learning ⋮ A Local Deep Learning Method for Solving High Order Partial Differential Equations ⋮ Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning ⋮ Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks ⋮ Solving High-Dimensional Optimal Stopping Problems Using Optimization Based Model Order Reduction ⋮ An efficient neural network method with plane wave activation functions for solving Helmholtz equation

Uses Software

Cites Work

This page was built for publication: Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations