Structure probing neural network deflation

Yiqi Gu

doi:10.1016/j.jcp.2021.110231

Structure probing neural network deflation

2021-06-01

10

OA

AI

DOI：10.1016/j.jcp.2021.110231

Original

Save

View PDF

Abstract

En 中文

Deep learning is a powerful tool for solving nonlinear differential equations, but usually, only the solution corresponding to the flattest local minimizer can be found due to the implicit regularization of stochastic gradient descent. This paper proposes a network-based structure probing deflation method to make deep learning capable of identifying multiple solutions that are ubiquitous and important in nonlinear physical models. First, we introduce deflation operators built with known solutions to make known solutions no longer local minimizers of the optimization energy landscape. Second, to facilitate the convergence to the desired local minimizer, a structure probing technique is proposed to obtain an initial guess close to the desired local minimizer. Together with neural network structures carefully designed in this paper, the new regularized optimization can converge to new solutions efficiently. Due to the mesh-free nature of deep learning, the proposed method is capable of solving high-dimensional problems on complicated domains with multiple solutions, while existing methods focus on merely one or two-dimensional regular domains and are more expensive in operation counts. Numerical experiments also demonstrate that the proposed method could find more solutions than exiting methods. (C) 2021 Elsevier Inc. All rights reserved.

Keywords:

Neural networks deflation

Structure probing

Nonlinear differential equations

High dimension

Deep least-square method

Convergence

Structure probing neural network deflation

Abstract

AI Summary

Journal

Organization