AutoAMG($θ$): An Auto-Tuned AMG Method Based on Deep Learning for Strong Threshold

AutoAMG($θ$): An Auto-Tuned AMG Method Based on Deep Learning for Strong Threshold

Year:    2024

Author:    Haifeng Zou, Xiaowen Xu, Chen-Song Zhang, Zeyao Mo

Communications in Computational Physics, Vol. 36 (2024), Iss. 1 : pp. 200–220

Abstract

Algebraic Multigrid (AMG) is one of the most widely used iterative algorithms for solving large sparse linear equations $Ax=b.$ In AMG, the coarse grid is a key component that affects the efficiency of the algorithm, the construction of which relies on the strong threshold parameter $θ.$ This parameter is generally chosen empirically, with a default value in many current AMG solvers of 0.25 for 2D problems and 0.5 for 3D problems. However, for many practical problems, the quality of the coarse grid and the efficiency of the AMG algorithm are sensitive to $θ;$ the default value is rarely optimal, and sometimes is far from it. Therefore, how to choose a better $θ$ is an important question. In this paper, we propose a deep learning based auto-tuning method, AutoAMG($θ$) for multiscale sparse linear equations, which are common in practical problems. The method uses Graph Neural Network (GNN) to extract matrix features, and a Multilayer Perceptron (MLP) to build the mapping between matrix features and the optimal $θ,$ which can adaptively predict $θ$ values for different matrices. Numerical experiments show that AutoAMG($θ$) can achieve significant speedup compared to the default $θ$ value.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/cicp.OA-2023-0072

Communications in Computational Physics, Vol. 36 (2024), Iss. 1 : pp. 200–220

Published online:    2024-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    21

Keywords:    AMG strong threshold graph neural network auto-tuning multiscale matrix.

Author Details

Haifeng Zou

Xiaowen Xu

Chen-Song Zhang

Zeyao Mo