Bilateral random projections

Zhou, T; Tao, D

Bilateral random projections

Zhou, T Tao, D

Permalink

Publication Type:: Conference Proceeding
Citation:: IEEE International Symposium on Information Theory - Proceedings, 2012, pp. 1286 - 1290
Issue Date:: 2012-10-22

Closed Access

	Filename	Description	Size
	2012004233OK.pdf		237.31 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhou, T	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2012-10-22	en_US
dc.identifier.citation	IEEE International Symposium on Information Theory - Proceedings, 2012, pp. 1286 - 1290	en_US
dc.identifier.isbn	9781467325790	en_US
dc.identifier.uri	http://hdl.handle.net/10453/22946
dc.description.abstract	Low-rank structure have been profoundly studied in data mining and machine learning. In this paper, we show a dense matrix X's low-rank approximation can be rapidly built from its left and right random projections Y 1 = XA 1 and Y 2 = X T A 2, or bilateral random projection (BRP). We then show power scheme can further improve the precision. The deterministic, average and deviation bounds of the proposed method and its power scheme modification are proved theoretically. The effectiveness and the efficiency of BRP based low-rank approximation is empirically verified on both artificial and real datasets. © 2012 IEEE.	en_US
dc.relation	http://purl.org/au-research/grants/arc/DP120103730
dc.relation.ispartof	IEEE International Symposium on Information Theory - Proceedings	en_US
dc.relation.isbasedon	10.1109/ISIT.2012.6283064	en_US
dc.title	Bilateral random projections	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
dc.location.activity	Cambridge, USA	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

Low-rank structure have been profoundly studied in data mining and machine learning. In this paper, we show a dense matrix X's low-rank approximation can be rapidly built from its left and right random projections Y 1 = XA 1 and Y 2 = X T A 2, or bilateral random projection (BRP). We then show power scheme can further improve the precision. The deterministic, average and deviation bounds of the proposed method and its power scheme modification are proved theoretically. The effectiveness and the efficiency of BRP based low-rank approximation is empirically verified on both artificial and real datasets. © 2012 IEEE.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/22946