Saved in:
Bibliographic Details
Main Authors: Burstein, Will, Iosevich, Alex, Nathan, Hari Sarang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.16345
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908783262826496
author Burstein, Will
Iosevich, Alex
Nathan, Hari Sarang
author_facet Burstein, Will
Iosevich, Alex
Nathan, Hari Sarang
contents We introduce a generalized Fourier ratio, the \(\ell^1/\ell^2\) norm ratio of coefficients in an \emph{arbitrary} orthonormal system, as a single, basis-invariant measure of \emph{effective dimension} that governs fundamental limits across signal recovery, localization, and learning. First, we prove that functions with small Fourier ratio can be stably recovered from random missing samples via \(\ell^1\) minimization, extending and clarifying compressed sensing guarantees for general bounded orthonormal systems. Second, we establish a sharp \emph{localization obstruction}: any attempt to localize recovery to subslices of a product space necessarily inflates the Fourier ratio by a factor scaling with the square root of the slice count, demonstrating that global complexity cannot be distributed locally. Finally, we show that the same parameter controls key complexity-theoretic measures: it provides explicit upper bounds on Kolmogorov rate-distortion description length and on the statistical query (SQ) dimension of the associated function class. These results unify analytic, algorithmic, and learning-theoretic constraints under a single complexity parameter, revealing the Fourier ratio as a fundamental invariant in information-theoretic signal processing.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16345
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Fourier Ratio: A Unifying Measure of Complexity for Recovery, Localization, and Learning
Burstein, Will
Iosevich, Alex
Nathan, Hari Sarang
Classical Analysis and ODEs
Information Theory
Functional Analysis
We introduce a generalized Fourier ratio, the \(\ell^1/\ell^2\) norm ratio of coefficients in an \emph{arbitrary} orthonormal system, as a single, basis-invariant measure of \emph{effective dimension} that governs fundamental limits across signal recovery, localization, and learning. First, we prove that functions with small Fourier ratio can be stably recovered from random missing samples via \(\ell^1\) minimization, extending and clarifying compressed sensing guarantees for general bounded orthonormal systems. Second, we establish a sharp \emph{localization obstruction}: any attempt to localize recovery to subslices of a product space necessarily inflates the Fourier ratio by a factor scaling with the square root of the slice count, demonstrating that global complexity cannot be distributed locally. Finally, we show that the same parameter controls key complexity-theoretic measures: it provides explicit upper bounds on Kolmogorov rate-distortion description length and on the statistical query (SQ) dimension of the associated function class. These results unify analytic, algorithmic, and learning-theoretic constraints under a single complexity parameter, revealing the Fourier ratio as a fundamental invariant in information-theoretic signal processing.
title The Fourier Ratio: A Unifying Measure of Complexity for Recovery, Localization, and Learning
topic Classical Analysis and ODEs
Information Theory
Functional Analysis
url https://arxiv.org/abs/2601.16345