Uniform error estimates for artificial neural network approximations for heat equations

11/20/2019
by   Lukas Gonon, et al.
0

Recently, artificial neural networks (ANNs) in conjunction with stochastic gradient descent optimization methods have been employed to approximately compute solutions of possibly rather high-dimensional partial differential equations (PDEs). Very recently, there have also been a number of rigorous mathematical results in the scientific literature which examine the approximation capabilities of such deep learning based approximation algorithms for PDEs. These mathematical results from the scientific literature prove in part that algorithms based on ANNs are capable of overcoming the curse of dimensionality in the numerical approximation of high-dimensional PDEs. In these mathematical results from the scientific literature usually the error between the solution of the PDE and the approximating ANN is measured in the L^p-sense with respect to some p ∈ [1,∞) and some probability measure. In many applications it is, however, also important to control the error in a uniform L^∞-sense. The key contribution of the main result of this article is to develop the techniques to obtain error estimates between solutions of PDEs and approximating ANNs in the uniform L^∞-sense. In particular, we prove that the number of parameters of an ANN to uniformly approximate the classical solution of the heat equation in a region [a,b]^d for a fixed time point T ∈ (0,∞) grows at most polynomially in the dimension d ∈N and the reciprocal of the approximation precision ε > 0. This shows that ANNs can overcome the curse of dimensionality in the numerical approximation of the heat equation when the error is measured in the uniform L^∞-norm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/03/2020

Space-time deep neural network approximations for high-dimensional partial differential equations

It is one of the most challenging issues in applied mathematics to appro...
research
12/08/2020

High-dimensional approximation spaces of artificial neural networks and applications to partial differential equations

In this paper we develop a new machinery to study the capacity of artifi...
research
11/21/2019

Trotter Kato Theorem for Bi Continuous Semigroups and Approximation of PDEs

In this paper, we introduce formulations of the Trotter Kato theorem for...
research
08/11/2019

Space-time error estimates for deep neural network approximations for differential equations

Over the last few years deep artificial neural networks (DNNs) have very...
research
11/08/2019

Generalised multilevel Picard approximations

It is one of the most challenging problems in applied mathematics to app...

Please sign up or login with your details

Forgot password? Click here to reset