Maxisets for Model Selection

Simple item page
dc.creatorAutin, Florent
dc.creatorPennec, Erwan Le
dc.creatorLoubes, Jean-Michel
dc.creatorRivoirard, Vincent
dc.date2008-02-28
dc.date2008-12-16
dc.date.accessioned2026-07-07T12:12:34Z
dc.date.available2026-07-07T12:12:34Z
dc.descriptionWe address the statistical issue of determining the maximal spaces (maxisets) where model selection procedures attain a given rate of convergence. By considering first general dictionaries, then orthonormal bases, we characterize these maxisets in terms of approximation spaces. These results are illustrated by classical choices of wavelet model collections. For each of them, the maxisets are described in terms of functional spaces. We take a special care of the issue of calculability and measure the induced loss of performance in terms of maxisets.
dc.identifierhttps://arxiv.org/abs/0802.4192
dc.identifierhttp://arxiv.org/abs/0802.4192
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/210588
dc.subjectStatistics Theory
dc.titleMaxisets for Model Selection
dc.typetext

Files

Collections

arXiv