Saved in:
Bibliographic Details
Main Author: Attali, Jean-Gabriel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.04914
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911361372520448
author Attali, Jean-Gabriel
author_facet Attali, Jean-Gabriel
contents We study approximation limits of single-hidden-layer neural networks with analytic activation functions under global coefficient constraints. Under uniform $\ell^1$ bounds, or more generally sub-exponential growth of the coefficients, we show that such networks generate model classes with strong quantitative regularity, leading to uniform analyticity of the realized functions. As a consequence, up to an exponentially small residual term, the error of best network approximation on generic target functions is bounded from below by the error of best polynomial approximation. In particular, networks with analytic activation functions with controlled coefficients cannot outperform classical polynomial approximation rates on non-analytic targets. The underlying rigidity phenomenon extends to smoother, non-analytic activations satisfying Gevrey-type regularity assumptions, yielding sub-exponential variants of the approximation barrier. The analysis is entirely deterministic and relies on a comparison argument combined with classical Bernstein-type estimates; extensions to higher dimensions are also discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04914
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Analytic Regularity and Approximation Limits of Coefficient-Constrained Shallow Networks
Attali, Jean-Gabriel
Mathematical Finance
We study approximation limits of single-hidden-layer neural networks with analytic activation functions under global coefficient constraints. Under uniform $\ell^1$ bounds, or more generally sub-exponential growth of the coefficients, we show that such networks generate model classes with strong quantitative regularity, leading to uniform analyticity of the realized functions. As a consequence, up to an exponentially small residual term, the error of best network approximation on generic target functions is bounded from below by the error of best polynomial approximation. In particular, networks with analytic activation functions with controlled coefficients cannot outperform classical polynomial approximation rates on non-analytic targets. The underlying rigidity phenomenon extends to smoother, non-analytic activations satisfying Gevrey-type regularity assumptions, yielding sub-exponential variants of the approximation barrier. The analysis is entirely deterministic and relies on a comparison argument combined with classical Bernstein-type estimates; extensions to higher dimensions are also discussed.
title Analytic Regularity and Approximation Limits of Coefficient-Constrained Shallow Networks
topic Mathematical Finance
url https://arxiv.org/abs/2601.04914