English

Barron Space Representations for Elliptic PDEs with Homogeneous Boundary Conditions

Numerical Analysis 2025-10-21 v2 Machine Learning Numerical Analysis Analysis of PDEs

Abstract

We study the approximation complexity of high-dimensional second-order elliptic PDEs with homogeneous boundary conditions on the unit hypercube, within the framework of Barron spaces. Under the assumption that the coefficients belong to suitably defined Barron spaces, we prove that the solution can be efficiently approximated by two-layer neural networks, circumventing the curse of dimensionality. Our results demonstrate the expressive power of shallow networks in capturing high-dimensional PDE solutions under appropriate structural assumptions.

Keywords

Cite

@article{arxiv.2508.07559,
  title  = {Barron Space Representations for Elliptic PDEs with Homogeneous Boundary Conditions},
  author = {Ziang Chen and Liqiang Huang},
  journal= {arXiv preprint arXiv:2508.07559},
  year   = {2025}
}