A single pretrained neural operator can act as a reusable local solver inside additive Schwarz iterations, solving elliptic PDEs with random microstructures on large, non-convex domains.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Learning-based Domain Decomposition Method
A single pretrained neural operator can act as a reusable local solver inside additive Schwarz iterations, solving elliptic PDEs with random microstructures on large, non-convex domains.