Nystrom type subsampling analyzed as a regularized projection
Loading...
Date
2016
Authors
Kriukova, Galyna
Pereverzyev, Sergei V.
Tkachenko, Pavlo
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In 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.
Description
Keywords
Citation
Kriukova Galyna. Nystrom type subsampling analyzed as a regularized projection / Galyna Kriukova, Sergiy Pereverzyev, Pavlo Tkachenko // Applied Mathematics. - 2016. - Nr. 22, January. - 19 p.