Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency

License: See LICENSE file · Updated 2026-09-26
My rating

The work targets neural operators used as differentiable surrogates for partial differential equation inverse problems, constrained optimization, design, and control. It directly supervises input-output sensitivities through derivative-informed training and proposes generating sketched tangent consistency information on-the-fly. This avoids dependence on offline-generated derivative labels that can be slow, storage-intensive, and difficult to adapt across datasets, resolutions, or perturbation bases.

Tags: