Two-Scale Localized PCA-Net: Coarse-Global and Local-Residual Representations for Artifact-Reduced PDE Operator Learning
Two-Scale Localized PCA-Net is introduced, which decomposes the solution into a coarse-global component and local residual corrections and provides an efficient representation for artifact-reduced PDE operator learning.
Mrigank Dhingra, J. Stout, O. San
· 0 citations