Adaptive complexity regularization for linear inverse problems

dc.creatorLoubes, Jean-Michel
dc.creatorLudeña, Carenne
dc.date2008-07-30
dc.date.accessioned2026-07-07T09:53:45Z
dc.date.available2026-07-07T09:53:45Z
dc.descriptionWe tackle the problem of building adaptive estimation procedures for ill-posed inverse problems. For general regularization methods depending on tuning parameters, we construct a penalized method that selects the optimal smoothing sequence without prior knowledge of the regularity of the function to be estimated. We provide for such estimators oracle inequalities and optimal rates of convergence. This penalized approach is applied to Tikhonov regularization and to regularization by projection.
dc.descriptionPublished in at http://dx.doi.org/10.1214/07-EJS115 the Electronic Journal of Statistics (http://www.i-journals.org/ejs/) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/0807.4859
dc.identifierhttp://arxiv.org/abs/0807.4859
dc.identifierElectronic Journal of Statistics 2008, Vol. 2, 661-677
dc.identifierdoi:10.1214/07-EJS115
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/166064
dc.subjectStatistics Theory
dc.subject62G05; 34K29 (Primary)
dc.titleAdaptive complexity regularization for linear inverse problems
dc.typetext

Files

Collections