A reduced order Schwarz method for nonlinear multiscale elliptic equations based on two-layer neural networks

Abstract

Neural networks are powerful tools for approximating high dimensional data that have been used in many contexts, including solution of partial differential equations (PDEs). We describe a solver for multiscale fully nonlinear elliptic equations that makes use of domain decomposition, an accelerated Schwarz framework, and two-layer neural networks to approximate the boundary-to-boundary map for the subdomains, which is the key step in the Schwarz procedure. Conventionally, the boundary-to-boundary map requires solution of boundary-value elliptic problems on each subdomain. By leveraging the compressibility of multiscale problems, our approach trains the neural network offline to serve as a surrogate for the usual implementation of the boundary-to-boundary map. Our method is applied to a multiscale semilinear elliptic equation and a multiscale $p$-Laplace equation. In both cases we demonstrate significant improvement in efficiency as well as good accuracy and generalization performance.

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Fourier Neural Operator for Parametric Partial Differential Equations
• Multi-scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains
• Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't
• Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
• Iterated numerical homogenization for multi-scale elliptic equations with monotone nonlinearity
• Schwarz iteration method for elliptic equation with rough media based on random sampling
• Manifold Learning and Nonlinear Homogenization

Cited by in corpus (1)

• Dynamic flux surrogate-based partitioned methods for interface problems