A sharp adaptive confidence ball for self-similar functions

From MaRDI portal
Publication:335671

DOI10.1016/J.SPA.2016.04.017zbMATH Open1348.62165arXiv1406.3994OpenAlexW23305736MaRDI QIDQ335671FDOQ335671


Authors: Richard Nickl, Botond Szabó Edit this on Wikidata


Publication date: 2 November 2016

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Abstract: In the nonparametric Gaussian sequence space model an ell2-confidence ball Cn is constructed that adapts to unknown smoothness and Sobolev-norm of the infinite-dimensional parameter to be estimated. The confidence ball has exact and honest asymptotic coverage over appropriately defined `self-similar' parameter spaces. It is shown by information-theoretic methods that this `self-similarity' condition is weakest possible.


Full work available at URL: https://arxiv.org/abs/1406.3994




Recommendations




Cites Work


Cited In (16)





This page was built for publication: A sharp adaptive confidence ball for self-similar functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q335671)