EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

$$L_2$$-norm sampling discretization and recovery of functions from RKHS with finite trace

Moritz Moeller, Tino Ullrich

Sampling Theory, Signal Processing, and Data Analysis · 2021

DOI: 10.1007/s43670-021-00013-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sampling Theory, Signal Processing, and Data Analysis, 2021. Verfasst von Moritz Moeller und 1 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper we study $$L_2$$ L 2 -norm sampling discretization and sampling recovery of complex-valued functions in RKHS on $$D \subset \mathbb {R}^d$$ D ⊂ R d based on random function samples. We only assume the finite trace of the kernel (Hilbert–Schmidt embedding into $$L_2$$ L 2 ) and provide several concrete estimates with precise constants for the corresponding worst-case errors. In general, our analysis does not need any additional assumptions and also includes the case of non-Mercer kernels and also non-separable RKHS. The fail probability is controlled and decays polynomially in n , the number of samples. Under the mild additional assumption of separability we observe improved rates of convergence related to the decay of the singular values. Our main tool is a spectral norm concentration inequality for infinite complex random matrices with independent rows complementing earlier results by Rudelson, Mendelson, Pajor, Oliveira and Rauhut.

Förderung

  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Moeller, M., & Ullrich, T. (2021). $$L_2$$-norm sampling discretization and recovery of functions from RKHS with finite trace. Sampling Theory, Signal Processing, and Data Analysis. https://doi.org/10.1007/s43670-021-00013-3

Vancouver

Moeller M, Ullrich T. $$L_2$$-norm sampling discretization and recovery of functions from RKHS with finite trace. Sampling Theory, Signal Processing, and Data Analysis. 2021. doi:10.1007/s43670-021-00013-3

BibTeX
@article{Moeller2021,
  author = {Moeller, Moritz and Ullrich, Tino},
  title = {$$L_2$$-norm sampling discretization and recovery of functions from RKHS with finite trace},
  journal = {Sampling Theory, Signal Processing, and Data Analysis},
  year = {2021},
  doi = {10.1007/s43670-021-00013-3}
}
Kostenlos starten →