cs.LGNov 10, 2026

Geometry-Dependent Approximation and Stability Properties of Shallow ReLUk^k Networks on Bounded Euclidean Domains

Authors: Yuqing Liu, Tong Mao, Jinchao Xu

Organizations: RPTU University Kaiserslautern-Landau, Kaiserslautern and Landau in der Pfalz, Rhineland-Palatinate, Germany · Shenzhen Loop Area Institute, Shenzhen 518000, P. R. China

Abstract

On bounded Euclidean domains, we study how hidden-parameter geometry affects shallow ReLUk^k networks through results on approximation rates, saturation-type lower bounds, Gram and stiffness matrix spectra, Bernstein and Marcinkiewicz--Zygmund inequalities, discrete least-squares recovery, and inverse approximation. Our analysis uses smooth localization and dyadic Fourier estimates. We quantify parameter geometry by the fill distance hh and antipodal separation distance h‾\underline h. For the prescribed network space LnkL_n^k, representative approximation estimates take the form \begin{equation*} \begin{aligned} \inf_{g_n\in L_n^k}|f-g_n|{\mathcal L^2(Ω')}&\lesssim h^r|f|{\mathcal H^r(Ω)},\ \inf_{g_n\in L_n^k}|f-g_n|{\mathcal L^2(Ω)}&\gtrsim \underline h^{\frac{d+2k+1}{2}}|f|{\mathcal L^2(Ω')}. \end{aligned} \end{equation*} The upper bound exploits target regularity up to the critical order d+2k+12\frac{d+2k+1}{2}, while the lower bound applies asymptotically to fixed targets smoother than this order. The upper estimate holds on an interior subdomain Ω′Ω', whereas the lower estimate concerns the larger domain ΩΩ. We also obtain geometry-dependent spectral estimates that quantify conditioning and coefficient stability. Further results establish norm discretization and regularized recovery from function values, and infer target regularity from approximation rates under coefficient or separation conditions. Altogether, these results describe how parameter geometry governs approximation accuracy, the stability of coefficient representations, discrete recovery, and the regularity information contained in convergence rates.

Explore similar work

CardsList
  1. Configuration-Dependent Lower Bounds for Approximation by Shallow ReLUk^k Networks on the Sphere

    Oct 5, 2025Tong Mao, Jinchao XuShallow Neural NetworksNeural Network Approximation Theory

  2. Boundary Geometry Determines Optimal Shallow ReLU Approximation under Weighted Coefficient Constraints

    Oct 27, 2026Jia-Qi Yang, Lei ShiNeural Network Approximation TheoryShallow Neural Networks

  3. Shallow ReLUs^s Networks in LpL^p-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization

    May 18, 2026Weizhao Li, Fanghui Liu, Lei ShiShallow Neural NetworksNonparametric Regression