Worst-case recovery guarantees for least squares approximation using random samples

TL;DR

This paper develops worst-case guarantees for least squares approximation methods using random samples, providing new bounds for hyperbolic Fourier and wavelet regression, and showing competitive performance with quasi-Monte Carlo techniques.

Contribution

It introduces explicit worst-case recovery guarantees for least squares approximation with random nodes across various function classes, including hyperbolic Fourier and wavelet regressions.

Findings

High-probability error bounds for hyperbolic Fourier regression.

Near-optimal worst-case error bounds for random cubature methods.

Competitive performance of simple random sampling methods against quasi-Monte Carlo approaches.

Abstract

We construct a least squares approximation method for the recovery of complex-valued functions from a reproducing kernel Hilbert space on $D \subset \mathbb{R}^d$. The nodes are drawn at random for the whole class of functions and the error is measured in $L_2(D,\varrho_D)$. We prove worst-case recovery guarantees by explicitly controlling all the involved constants. This leads to new preasymptotic recovery bounds with high probability for the error of Hyperbolic Fourier Regression on multivariate data. In addition, we further investigate its counterpart Hyperbolic Wavelet Regression also based on least-squares to recover non-periodic functions from random samples. Finally, we reconsider the analysis of a cubature method based on plain random points with optimal weights and reveal near-optimal worst-case error bounds with high probability. It turns out that this simple method can compete with the quasi-Monte Carlo methods in the literature which are based on lattices and digital nets.