Multigrid plus neural-network acceleration reduces the cost of phi-FEM while preserving accuracy in 2D and 3D test cases.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A multigrid and neural network approach to reduce the computational cost of phi-FEM
Multigrid plus neural-network acceleration reduces the cost of phi-FEM while preserving accuracy in 2D and 3D test cases.