High-dimensional stochastic optimization with the generalized Dantzig estimator

Simple item page
dc.creatorLounici, Karim
dc.date2008-11-14
dc.date.accessioned2026-07-07T10:18:23Z
dc.date.available2026-07-07T10:18:23Z
dc.descriptionWe propose a generalized version of the Dantzig selector. We show that it satisfies sparsity oracle inequalities in prediction and estimation. We consider then the particular case of high-dimensional linear regression model selection with the Huber loss function. In this case we derive the sup-norm convergence rate and the sign concentration property of the Dantzig estimators under a mutual coherence assumption on the dictionary.
dc.identifierhttps://arxiv.org/abs/0811.2281
dc.identifierhttp://arxiv.org/abs/0811.2281
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/174168
dc.subjectStatistics Theory
dc.subject62G25 ; 62G05
dc.titleHigh-dimensional stochastic optimization with the generalized Dantzig estimator
dc.typetext

Files

Collections

arXiv