On non-asymptotic bounds for estimation in generalized linear models with highly correlated design

Simple item page
dc.creatorvan de Geer, Sara A.
dc.date2007-09-06
dc.date.accessioned2026-07-07T08:28:40Z
dc.date.available2026-07-07T08:28:40Z
dc.descriptionWe study a high-dimensional generalized linear model and penalized empirical risk minimization with $\ell_1$ penalty. Our aim is to provide a non-trivial illustration that non-asymptotic bounds for the estimator can be obtained without relying on the chaining technique and/or the peeling device.
dc.descriptionPublished at http://dx.doi.org/10.1214/074921707000000319 in the IMS Lecture Notes Monograph Series (http://www.imstat.org/publications/lecnotes.htm) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/0709.0844
dc.identifierhttp://arxiv.org/abs/0709.0844
dc.identifierIMS Lecture Notes Monograph Series 2007, Vol. 55, 121-134
dc.identifierdoi:10.1214/074921707000000319
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/137697
dc.subjectStatistics Theory
dc.subject62G08 (Primary)
dc.titleOn non-asymptotic bounds for estimation in generalized linear models with highly correlated design
dc.typetext

Files

Collections

arXiv