A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations

Abstract

Deep neural networks and other deep learning methods have very successfully been applied to the numerical approximation of high-dimensional nonlinear parabolic partial differential equations (PDEs), which are widely used in finance, engineering, and natural sciences. In particular, simulations indicate that algorithms based on deep learning overcome the curse of dimensionality in the numerical approximation of solutions of semilinear PDEs. For certain linear PDEs this has also been proved mathematically. The key contribution of this article is to rigorously prove this for the first time for a class of nonlinear PDEs. More precisely, we prove in the case of semilinear heat equations with gradient-independent nonlinearities that the numbers of parameters of the employed deep neural networks grow at most polynomially in both the PDE dimension and the reciprocal of the prescribed approximation accuracy. Our proof relies on recently introduced multilevel Picard approximations of semilinear PDEs.

arXiv comment29 pages

References in corpus (9)

• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order 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
• A Deep Neural Network Surrogate for High-Dimensional Random Partial Differential Equations
• Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
• Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks
• Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations

Cited by in corpus (19)

• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
• Convergence of the Deep BSDE Method for Coupled FBSDEs
• DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing
• Multilevel Picard iterations for solving smooth semilinear parabolic heat equations
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks
• Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations
• Full error analysis for the training of deep neural networks
• Efficient approximation of high-dimensional functions with neural networks
• Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes
• Numerical methods for backward stochastic differential equations: A survey
• Uniform error estimates for artificial neural network approximations for heat equations
• Variational Monte Carlo - Bridging Concepts of Machine Learning and High Dimensional Partial Differential Equations
• Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
• Deep learning algorithms for solving high dimensional nonlinear backward stochastic differential equations
• Residual Multi-Fidelity Neural Network Computing
• Neural Network Solutions to Differential Equations in Non-Convex Domains: Solving the Electric Field in the Slit-Well Microfluidic Device
• Universal Fourier Neural Operators for periodic homogenization problems in linear elasticity