Bagging Regularizes

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7268

Full metadata record

DC Field	Value	Language
dc.creator	Poggio, Tomaso	-
dc.creator	Rifkin, Ryan	-
dc.creator	Mukherjee, Sayan	-
dc.creator	Rakhlin, Alex	-
dc.date	2004-10-20T21:04:57Z	-
dc.date	2004-10-20T21:04:57Z	-
dc.date	2002-03-01	-
dc.date.accessioned	2013-10-09T02:48:52Z	-
dc.date.available	2013-10-09T02:48:52Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-2002-003	-
dc.identifier	CBCL-214	-
dc.identifier	http://hdl.handle.net/1721.1/7268	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	Intuitively, we expect that averaging --- or bagging --- different regressors with low correlation should smooth their behavior and be somewhat similar to regularization. In this note we make this intuition precise. Using an almost classical definition of stability, we prove that a certain form of averaging provides generalization bounds with a rate of convergence of the same order as Tikhonov regularization --- similar to fashionable RKHS-based learning algorithms.	-
dc.format	7 p.	-
dc.format	906324 bytes	-
dc.format	285651 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-2002-003	-
dc.relation	CBCL-214	-
dc.subject	AI	-
dc.subject	Bagging	-
dc.subject	stability	-
dc.subject	regularization	-
dc.title	Bagging Regularizes	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI