Empirical and Gaussian processes on Besov classes

Richard Nickl

doi:10.1214/074921706000000842

Empirical and Gaussian processes on Besov classes

Probability 2007-05-23 v1 Functional Analysis

Authors: Richard Nickl

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

We give several conditions for pregaussianity of norm balls of Besov spaces defined over $\mathbb{R}^d$ by exploiting results in Haroske and Triebel (2005). Furthermore, complementing sufficient conditions in Nickl and P\"{o}tscher (2005), we give necessary conditions on the parameters of the Besov space to obtain the Donsker property of such balls. For certain parameter combinations Besov balls are shown to be pregaussian but not Donsker.

Keywords

function spaces

Cite

@article{arxiv.math/0612706,
  title  = {Empirical and Gaussian processes on Besov classes},
  author = {Richard Nickl},
  journal= {arXiv preprint arXiv:math/0612706},
  year   = {2007}
}

Comments

Published at http://dx.doi.org/10.1214/074921706000000842 in the IMS Lecture Notes Monograph Series (http://www.imstat.org/publications/lecnotes.htm) by the Institute of Mathematical Statistics (http://www.imstat.org)

Empirical and Gaussian processes on Besov classes

Abstract

Keywords

Cite

Comments

Related papers