Log In Sign Up

A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations

by   Jianfeng Lu, et al.

This paper concerns the a priori generalization analysis of the Deep Ritz Method (DRM) [W. E and B. Yu, 2017], a popular neural-network-based method for solving high dimensional partial differential equations. We derive the generalization error bounds of two-layer neural networks in the framework of the DRM for solving two prototype elliptic PDEs: Poisson equation and static Schrödinger equation on the d-dimensional unit hypercube. Specifically, we prove that the convergence rates of generalization errors are independent of the dimension d, under the a priori assumption that the exact solutions of the PDEs lie in a suitable low-complexity space called spectral Barron space. Moreover, we give sufficient conditions on the forcing term and the potential function which guarantee that the solutions are spectral Barron functions. We achieve this by developing a new solution theory for the PDEs on the spectral Barron space, which can be viewed as an analog of the classical Sobolev regularity theory for PDEs.


page 1

page 2

page 3

page 4


On the Representation of Solutions to Elliptic PDEs in Barron Spaces

Numerical solutions to high-dimensional partial differential equations (...

Priori Error Estimate of Deep Mixed Residual Method for Elliptic PDEs

In this work, we derive a priori error estimate of the mixed residual me...

A Regularity Theory for Static Schrödinger Equations on ℝ^d in Spectral Barron Spaces

Spectral Barron spaces have received considerable interest recently as i...

Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality

In this paper, we study the statistical limits of deep learning techniqu...

Scheduled Relaxation Jacobi schemes for non-elliptic partial differential equations

The Scheduled Relaxation Jacobi (SRJ) method is a linear solver algorith...