A neural operator is trained once including a PDE residual penalty and then reused inside gradient-based optimization to solve multiple PDE-constrained tracking control problems.
Learning nonlinear operators via deeponet based on the universal approximation theorem of operators
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Employing Deep Neural Operators for PDE control by decoupling training and optimization
A neural operator is trained once including a PDE residual penalty and then reused inside gradient-based optimization to solve multiple PDE-constrained tracking control problems.