Fourier Residual Networks Achieve Spectral Accuracy for Discontinuous Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Davis, Owen, Motamed, Mohammad, Runborg, Olof
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914530721792000
author Davis, Owen
Motamed, Mohammad
Runborg, Olof
author_facet Davis, Owen
Motamed, Mohammad
Runborg, Olof
contents We present a constructive approximation framework for analyzing the expressive power of Fourier residual networks in approximating a broad class of one-dimensional functions. Our study covers both piecewise continuous functions -- including those with jump discontinuities in the function and its derivatives -- and fully smooth functions. We show that Fourier residual networks achieve spectral convergence without requiring periodicity or continuity, thereby overcoming key limitations of classical linear Fourier approximation and nonlinear methods, without being restricted to Barron-type function spaces. Our approach builds on classical techniques from approximation theory, including fixed-point iteration and Hermite interpolation by trigonometric polynomials. We support our theoretical results with numerical experiments based on both the constructed approximations and a randomized algorithm developed in our earlier work.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03549
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fourier Residual Networks Achieve Spectral Accuracy for Discontinuous Functions
Davis, Owen
Motamed, Mohammad
Runborg, Olof
Numerical Analysis
Primary 41Axx, Secondary 68T07, 65T40
We present a constructive approximation framework for analyzing the expressive power of Fourier residual networks in approximating a broad class of one-dimensional functions. Our study covers both piecewise continuous functions -- including those with jump discontinuities in the function and its derivatives -- and fully smooth functions. We show that Fourier residual networks achieve spectral convergence without requiring periodicity or continuity, thereby overcoming key limitations of classical linear Fourier approximation and nonlinear methods, without being restricted to Barron-type function spaces. Our approach builds on classical techniques from approximation theory, including fixed-point iteration and Hermite interpolation by trigonometric polynomials. We support our theoretical results with numerical experiments based on both the constructed approximations and a randomized algorithm developed in our earlier work.
title Fourier Residual Networks Achieve Spectral Accuracy for Discontinuous Functions
topic Numerical Analysis
Primary 41Axx, Secondary 68T07, 65T40
url https://arxiv.org/abs/2605.03549