DocumentCode
28150
Title
Near-Optimal Coresets for Least-Squares Regression
Author
Boutsidis, Christos ; Drineas, Petros ; Magdon-Ismail, Malik
Author_Institution
Dept. of Math. Sci., IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA
Volume
59
Issue
10
fYear
2013
fDate
Oct. 2013
Firstpage
6880
Lastpage
6892
Abstract
We study the (constrained) least-squares regression as well as multiple response least-squares regression and ask the question of whether a subset of the data, a coreset, suffices to compute a good approximate solution to the regression. We give deterministic, low-order polynomial-time algorithms to construct such coresets with approximation guarantees, together with lower bounds indicating that there is not much room for improvement upon our results.
Keywords
least squares approximations; regression analysis; approximate solution; least squares regression; near optimal coresets; polynomial time algorithms; Approximation algorithms; Approximation methods; Distributed databases; Electronic mail; Linear regression; Time series analysis; Vectors; Least mean square algorithms; machine learning algorithms; regression analysis;
fLanguage
English
Journal_Title
Information Theory, IEEE Transactions on
Publisher
ieee
ISSN
0018-9448
Type
jour
DOI
10.1109/TIT.2013.2272457
Filename
6555821
Link To Document