On universal approximation and error bounds for Fourier Neural Operators
From MaRDI portal
Abstract: Fourier neural operators (FNOs) have recently been proposed as an effective framework for learning operators that map between infinite-dimensional spaces. We prove that FNOs are universal, in the sense that they can approximate any continuous operator to desired accuracy. Moreover, we suggest a mechanism by which FNOs can approximate operators associated with PDEs efficiently. Explicit error bounds are derived to show that the size of the FNO, approximating operators associated with a Darcy type elliptic PDE and with the incompressible Navier-Stokes equations of fluid dynamics, only increases sub (log)-linearly in terms of the reciprocal of the error. Thus, FNOs are shown to efficiently approximate operators arising in a large class of PDEs.
Cited in
(5)- Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method
- A neural operator view on U-Nets for inverse imaging problems
- FrFNO:Injecting the analytic Mittag-Leffler propagator into a resolution-robust neural operator for space-time fractional PDEs
- Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver
- Improving Learning of Green's Functions Through Kernel Decomposition
This page was built for publication: On universal approximation and error bounds for Fourier Neural Operators
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6372934)
