Show simple item record

dc.contributor.authorKlopp, Olga
dc.date.accessioned2012-03-02T12:06:40Z
dc.date.available2012-03-02T12:06:40Z
dc.date.issued2014
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/8352
dc.language.isoenen
dc.subjecthigh-dimensional sparse modelen
dc.subjectunknown varianceen
dc.subjectlow rank matrix estimationen
dc.subjectmatrix completionen
dc.subject.ddc519en
dc.titleNoisy low-rank matrix completion with general sampling distributionen
dc.typeArticle accepté pour publication ou publié
dc.contributor.editoruniversityotherCentre de Recherche en Économie et Statistique (CREST) http://www.crest.fr/ INSEE – École Nationale de la Statistique et de l'Administration Économique;France
dc.description.abstractenIn the present paper we consider the problem of matrix completion with noise for general sampling schemes. Unlike previous works, in our construction we do not need to know or to evaluate the sampling distribution or the variance of the noise. We propose new nuclear-norm penalized estimators, one of them of the ''square-root'' type. We prove that, up to a logarithmic factor, our estimators achieve optimal rates with respect to the estimation error.en
dc.relation.isversionofjnlnameBernoulli
dc.relation.isversionofjnlvol20
dc.relation.isversionofjnlissue1
dc.relation.isversionofjnldate2014
dc.relation.isversionofjnlpages1-393
dc.relation.isversionofdoihttp://dx.doi.org/10.3150/12-BEJ486
dc.identifier.urlsitehttp://hal.archives-ouvertes.fr/hal-00675413en
dc.description.sponsorshipprivateouien
dc.relation.isversionofjnlpublisherBernoulli Society for Mathematical Statistics and Probability
dc.subject.ddclabelProbabilités et mathématiques appliquéesen


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record