From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
Nisha Chandramoorthy, Daniel Sanz-Alonso, Nathan Waniorek
stat.ML, cs.LG, math.NA
Submitted: 2026-07-01
Comments: 66 pages
License: http://creativecommons.org/licenses/by/4.0/
The gist: We establish approximation and learning guarantees for Fourier neural operators (FNOs) applied to time- T solution operators of dissipative evolution equations.
Terminology
Abstract
We establish approximation and learning guarantees for Fourier neural operators (FNOs) applied to time- T solution operators of dissipative evolution equations. The analysis builds on the premise that FNOs can efficiently approximate and learn solution operators whenever these operators admit stable and accurate spectral discretizations. To formalize this idea, we introduce classes of evolution operators defined through spectral methods and derive FNO approximation bounds and polynomial sample complexity guarantees for these classes. For equations with polynomial nonlinearities, the learning rates depend primarily on the smoothness of the input space and the dimension of the physical domain. Our results hold uniformly over broad families of dissipative equations, rather than for a single fixed PDE, and apply in particular to the Navier--Stokes, Allen--Cahn, and Cahn--Hilliard equations. For equations with non-polynomial smooth nonlinearities, we prove that polynomial sample complexity still holds with rates that now additionally depend on the smoothness of the nonlinear terms and the dissipation strength. Overall, we connect classical spectral approximation theory with modern operator learning and explain when FNOs can learn nonlinear evolution operators efficiently.
Sources
- The Sample Complexity of Learning Lipschitz Operators with respect to Gaussian Measures
- Convergence Rates for Learning Pseudo-Differential Operators
- Optimal Multiscale Learning of Linear Operators
- Error analysis for learning the time-stepping operator of evolutionary PDEs
- Fourier Neural Operator for Plasma Modelling
- Data Complexity Estimates for Operator Learning
- Discretization Error of Fourier Neural Operators
- Continuous Data Assimilation with Learned Surrogate Dynamics
- Operator learning meets inverse problems: A probabilistic perspective
- FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
- Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
- Operator Learning: A Statistical Perspective
- Operator learning for hyperbolic partial differential equations
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches