Deflation vectors taken from a trained DeepONet, via trunk functions or predicted solutions, reduce PCG iteration counts across varied parametric PDE benchmarks.
DeepONet based preconditioning strategies for solving parametric linear systems of equations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Operator Learning to Accelerate Convergence of the Preconditioned Conjugate Gradient Method
Deflation vectors taken from a trained DeepONet, via trunk functions or predicted solutions, reduce PCG iteration counts across varied parametric PDE benchmarks.