Accelerating algebraic multigrid methods via artificial neural networks

DOI10.1007/s10013-022-00597-wMaRDI QIDQ2679755

Luca Dedè, Paola Francesca Antonietti, Matteo Caldana

Publication date: 23 January 2023

Published in: Vietnam Journal of Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2111.01629

zbMATH Keywords

finite element method; Stokes problem; elliptic PDEs; convolutional neural networks; deep learning; algebraic multigrid (AMG)

Mathematics Subject Classification ID

65N55: Multigrid methods; domain decomposition for boundary value problems involving PDEs

68T07: Artificial neural networks and deep learning

76D07: Stokes and related (Oseen, etc.) flows

65N12: Stability and convergence of numerical methods for boundary value problems involving PDEs

65N30: Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs

68T01: General topics in artificial intelligence

65N22: Numerical solution of discretized equations for boundary value problems involving PDEs

Uses Software

• hypre
• Seaborn
• ImageNet
• Statsmodels
• RMSprop
• Adam
• AlexNet
• PETSc/TS

Cites Work

• Statsmodels