English

Sampling numbers of smoothness classes via $\ell^1$-minimization

Numerical Analysis 2023-08-02 v3 Numerical Analysis

Abstract

Using techniques developed recently in the field of compressed sensing we prove new upper bounds for general (nonlinear) sampling numbers of (quasi-)Banach smoothness spaces in L2L^2. In particular, we show that in relevant cases such as mixed and isotropic weighted Wiener classes or Sobolev spaces with mixed smoothness, sampling numbers in L2L^2 can be upper bounded by best nn-term trigonometric widths in LL^\infty. We describe a recovery procedure from mm function values based on 1\ell^1-minimization (basis pursuit denoising). With this method, a significant gain in the rate of convergence compared to recently developed linear recovery methods is achieved. In this deterministic worst-case setting we see an additional speed-up of m1/2m^{-1/2} (up to log factors) compared to linear methods in case of weighted Wiener spaces. For their quasi-Banach counterparts even arbitrary polynomial speed-up is possible. Surprisingly, our approach allows to recover mixed smoothness Sobolev functions belonging to SprW(Td)S^r_pW(\mathbb{T}^d) on the dd-torus with a logarithmically better rate of convergence than any linear method can achieve when 1<p<21 < p < 2 and dd is large. This effect is not present for isotropic Sobolev spaces.

Keywords

Cite

@article{arxiv.2212.00445,
  title  = {Sampling numbers of smoothness classes via $\ell^1$-minimization},
  author = {Thomas Jahn and Tino Ullrich and Felix Voigtlaender},
  journal= {arXiv preprint arXiv:2212.00445},
  year   = {2023}
}
R2 v1 2026-06-28T07:19:19.272Z