Learning Optimal Multigrid Smoothers via Neural Networks
SIAM Journal on Scientific Computing · 2023-06 · 45 (3) · S199-S225
DOI: 10.1137/21m1430030 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 24.08.2022. Verfasst von Ru Huang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Multigrid methods are one of the most efficient techniques for solving large sparse linear systems arising from partial differential equations (PDEs) and graph Laplacians from machine learning applications. One of the key components of multigrid is smoothing, which aims at reducing high-frequency errors on each grid level. However, finding optimal smoothing algorithms is problem-dependent and can impose challenges for many problems. In this paper, we propose an efficient adaptive framework for learning optimized smoothers from operator stencils in the form of convolutional neural networks (CNNs). The CNNs are trained on small-scale problems from a given type of PDEs based on a supervised loss function derived from multigrid convergence theories and can be applied to large-scale problems of the same class of PDEs. Numerical results on anisotropic rotated Laplacian problems and variable coefficient diffusion problems demonstrate improved convergence rates and solution time compared with classical hand-crafted relaxation methods.
Förderung
- National Science Foundation
Zitieren
APA
Huang, R., Li, R., & Xi, Y. (2023). Learning Optimal Multigrid Smoothers via Neural Networks. SIAM Journal on Scientific Computing, 45(3), S199-S225. https://doi.org/10.1137/21m1430030
Vancouver
Huang R, Li R, Xi Y. Learning Optimal Multigrid Smoothers via Neural Networks. SIAM Journal on Scientific Computing. 2023;45(3):S199-S225. doi:10.1137/21m1430030
BibTeX
@article{Huang2023,
author = {Huang, Ru and Li, Ruipeng and Xi, Yuanzhe},
title = {Learning Optimal Multigrid Smoothers via Neural Networks},
journal = {SIAM Journal on Scientific Computing},
year = {2023},
volume = {45},
number = {3},
pages = {S199--S225},
doi = {10.1137/21m1430030}
}
EUVIMED