SelectNet: Self-paced learning for high-dimensional partial differential equations

doi:10.1016/j.jcp.2021.110444

SelectNet: Self-paced learning for high-dimensional partial differential equations

2021-09-01

35

OA

AI

DOI：10.1016/j.jcp.2021.110444

Original

Save

View PDF

Abstract

En 中文

The least squares method with deep neural networks as function parametrization has been applied to solve certain high-dimensional partial differential equations (PDEs) successfully; however, its convergence is slow and might not be guaranteed even within a simple class of PDEs. To improve the convergence of the network-based least squares model, we introduce a novel self-paced learning framework, SelectNet, which quantifies the difficulty of training samples, treats samples equally in the early stage of training, and slowly explores more challenging samples, e.g., samples with larger residual errors, mimicking the human cognitive process for more efficient learning. In particular, a selection network and the PDE solution network are trained simultaneously; the selection network adaptively weighting the training samples of the solution network achieving the goal of self-paced learning. Numerical examples indicate that the proposed SelectNet model outperforms existing models on the convergence speed and the convergence robustness, especially for low-regularity solutions. (c) 2021 Elsevier Inc. All rights reserved.

Keywords:

High-dimensional PDEs

Deep neural networks

Self-paced learning

Selected sampling

Least square method

Convergence

SelectNet: Self-paced learning for high-dimensional partial differential equations

Abstract

AI Summary

Journal

Organization