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

Oct 5, 2025

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

We establish two related but logically distinct results for shallow ReLUk^k neural networks on the unit sphere \SSd\SS^d. First, for an arbitrary set of inner neural-network parameters, the best L2(\SSd)\mathcal{L}^2(\SS^d) approximation of a fixed target function with smoothness r>d+2k+12r>\tfrac{d+2k+1}{2} admits an asymptotic lower bound given by a constant multiple of n−1/2h‾k+1/2n^{-1/2}\underline{h}^{k+1/2}, where h‾\underline{h} denotes the antipodal separation distance of the normalized inner-parameter set. This lower bound depends explicitly on the parameter configuration through h‾\underline{h} and applies without additional assumptions on the parameters. Second, for antipodally quasi-uniform parameters, h‾≃n−1/d\underline{h}\simeq n^{-1/d}, and the lower bound establishes the exact saturation order n−d+2k+12dn^{-\frac{d+2k+1}{2d}} for such parameter families: a target function with regularity greater than d+2k+12\frac{d+2k+1}{2} and satisfying the required parity condition can be approximated at this rate, whereas approximation at any strictly faster rate forces the target function to be zero. Our results therefore place linearized neural-network approximation within the classical saturation framework and show that, although ReLUk^k network spaces can outperform finite elements of the same degree, this advantage is intrinsically limited.
Oct 27, 2026

Boundary Geometry Determines Optimal Shallow ReLU Approximation under Weighted Coefficient Constraints

We study how boundary geometry affects LqL^q approximation by shallow ReLU neural networks on convex bodies K⊂RdK\subset\mathbb R^d. The target classes are unit balls of weighted variation spaces that can enlarge classical spaces by incorporating domain geometry into constraints on output coefficients. We establish upper and lower bounds for arbitrary convex bodies and determine the optimal polynomial approximation exponents for all planar convex bodies and their products with polytopes, including cubes and circular cylinders. For C2C^2 convex bodies, we determine the optimal exponents in a dimension-dependent range of qq extending beyond 22. When all principal curvatures are positive, the result extends to every finite q≥2q\ge2. For these classes, the dependence of the optimal exponent on the domain is captured by a single geometric growth exponent associated with small boundary caps. We also identify sharp weight thresholds for retaining the classical approximation exponent and improve previous weights on Euclidean balls while preserving the classical L2L^2 approximation rate. When the target is given as a finite ReLU network, the upper bounds can be realized by a compressed network using only the original neurons, without increasing the weighted coefficient sum. These results show that boundary geometry can change the optimal exponent even when dimension, error norm, and weighting rule are fixed.
May 18, 2026

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

This paper studies approximation by shallow ReLUs^s networks, σs(t)=max⁡{0,t}sσ_s(t)=\max\{0,t\}^s, together with their generalization behavior under ℓ1\ell_1 path-norm control. For the LpL^p-type integral spaces F~p,τd,s\widetilde{\mathcal{F}}_{p,τ_d,s}, 1≤p≤21\le p\le2, spherical harmonic analysis yields approximation bounds for shallow networks. In particular, when τdτ_d is the uniform measure and 1≤p<21\le p<2, the approximation rate is O ⁣(m−p(2s+2d+1)−2d2dp)O\!\left(m^{-\frac{p(2s+2d+1)-2d}{2dp}}\right) for 1≤p≤p∗1\le p\le p^* and O ⁣(m−p(4s+3d−1)−2d+24dp)O\!\left(m^{-\frac{p(4s+3d-1)-2d+2}{4dp}}\right) for p∗<p<2p^*<p<2, where p∗=2d+2d+3p^*=\frac{2d+2}{d+3}. Approximation bounds for Sobolev spaces Wα,pW^{α,p}, 1≤p<21\le p<2, are obtained through embeddings into spectral Barron spaces. For nonparametric regression with sub-Gaussian noise, path-norm-regularized shallow ReLUs^s networks achieve minimax-optimal rates O ⁣(n−d+2s+12d+2s+1log⁡n)O\!\left(n^{-\frac{d+2s+1}{2d+2s+1}}\log n\right) over Bs\mathscr{B}_s and O ⁣(n−2α2α+dlog⁡n)O\!\left(n^{-\frac{2α}{2α+d}}\log n\right) over Wα,∞W^{α,\infty}, with matching lower bounds up to logarithmic factors.