Nystrom type subsampling analyzed as a regularized projection

Simple item page
dc.contributor.authorKriukova, Galyna
dc.contributor.authorPereverzyev, Sergei V.
dc.contributor.authorTkachenko, Pavlo
dc.date.accessioned2017-06-14T15:00:24Z
dc.date.available2017-06-14T15:00:24Z
dc.date.issued2016
dc.description.abstractIn the statistical learning theory the Nystr¨om type subsampling methods are considered as tools for dealing with big data. In this paper we consider Nystr¨om subsampling as a special form of the projected Lavrentiev regularization, and study it using the approaches developed in the regularization theory. As a result, we prove that the same capacity independent learning rates that are quaranteed for standard algorithms running with quadratic computational complexity can be obtained with subquadratic complexity by the Nystr¨om subsampling approach, provided that the subsampling size is chosen properly. We propose a priori rule for choosing the subsampling size and a posteriori strategy for dealing with uncertainty in the choice of it. The theoretical results are illustrated by numerical experiments.uk
dc.identifier.citationKriukova Galyna. Nystrom type subsampling analyzed as a regularized projection / Galyna Kriukova, Sergiy Pereverzyev, Pavlo Tkachenko // Applied Mathematics. - 2016. - Nr. 22, January. - 19 p.uk
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/11581
dc.language.isoenuk
dc.relation.sourceApplied Mathematicsuk
dc.statuspublished earlieruk
dc.titleNystrom type subsampling analyzed as a regularized projectionuk
dc.typePreprintuk
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Kriukova_Nystr¨om_type_subsampling.pdf
Size:
502.58 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
7.54 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Кафедра математики