Interpolating Neural Operator (INO): A Data-Free and Efficient Approach for Learning PDE Solution Operators

License: See LICENSE file · Updated 2026-09-29
My rating

The paper targets neural operator learning for parametric partial differential equations across scientific computing domains. It introduces the Interpolating Neural Operator, a data-free interpolating neural network trained directly on the weak form of the PDE, avoiding dependence on large simulation datasets or lengthy physics-informed GPU training.

Tags: