REVIEW 2 cited by
Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
read the original abstract
We study learning-theoretic foundations of operator learning, using the linear layer of the Fourier Neural Operator architecture as a model problem. First, we identify three main errors that occur during the learning process: statistical error due to finite sample size, truncation error from finite rank approximation of the operator, and discretization error from handling functional data on a finite grid of domain points. Finally, we analyze a Discrete Fourier Transform (DFT) based least squares estimator, establishing both upper and lower bounds on the aforementioned errors.
Forward citations
Cited by 2 Pith papers
-
From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
FNOs achieve polynomial sample complexity for learning time-T solution operators of dissipative evolution equations when those operators admit stable spectral discretizations, with rates depending on smoothness, dimen...
-
Operator learning for the 2D incompressible Navier-Stokes equations: a conformal prediction approach in the data-scarce regime
A perturbation-based conformal prediction wrapper on Fourier Neural Operators yields narrower uncertainty bands than prior methods for 2D incompressible Navier-Stokes while preserving coverage in data-scarce regimes.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.