L^p sampling numbers for the Fourier-analytic Barron space

arXiv2208.07605MaRDI QIDQ6407980FDOQ6407980

Authors: Felix Voigtlaender 

Publication date: 16 August 2022

Abstract: In this paper, we consider Barron functions $f:[0,1{]}^{d}omathbbR$ of smoothness $sigma>0$, which are functions that can be written as [ f(x) = int_{mathbb{R}^d} F(xi) , e^{2 pi i langle x, xi angle} , d xi quad ext{with} quad int_{mathbb{R}^d} |F(xi)| cdot (1 + |xi|)^{sigma} , d xi < infty. ] For $sigma=1$, these functions play a prominent role in machine learning, since they can be efficiently approximated by (shallow) neural networks without suffering from the curse of dimensionality. For these functions, we study the following question: Given $m$ point samples $f(x_1),dots,f(x_m)$ of an unknown Barron function $f:[0,1{]}^{d}omathbbR$ of smoothness $sigma$, how well can $f$ be recovered from these samples, for an optimal choice of the sampling points and the reconstruction procedure? Denoting the optimal reconstruction error measured in $L^p$ by $s_m(sigma;L^p)$, we show that [ m^{- frac{1}{max { p,2 }} - frac{sigma}{d}} lesssim s_m(sigma;L^p) lesssim (ln (e + m))^{alpha(sigma,d) / p} cdot m^{- frac{1}{max { p,2 }} - frac{sigma}{d}} , ] where the implied constants only depend on $sigma$ and $d$ and where $alpha(sigma,d)$ stays bounded as $doinfty$.

Mathematics Subject Classification ID

Multidimensional problems (41A63) Function spaces arising in harmonic analysis (42B35) Banach spaces of continuous, differentiable or analytic functions (46E15) Algorithms for approximation of functions (65D15) Rate of convergence, degree of approximation (41A25) Sampling theory in information and communication theory (94A20) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

This page was built for publication: $L^p$ sampling numbers for the Fourier-analytic Barron space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6407980)