Statistical Learning: Stability is Sufficient for Generalization and Necessary and Sufficient for Consistency of Empirical Risk Minimization

dc.creator	Mukherjee, Sayan
dc.creator	Niyogi, Partha
dc.creator	Poggio, Tomaso
dc.creator	Rifkin, Ryan
dc.date	2004-08-31T18:12:01Z
dc.date	2004-08-31T18:12:01Z
dc.date	2002-12-01
dc.date.accessioned	2013-10-09T02:39:53Z
dc.date.available	2013-10-09T02:39:53Z
dc.date.issued	2013-10-09
dc.identifier	AIM-2002-024
dc.identifier	CBCL-223
dc.identifier	http://hdl.handle.net/1721.3/5507
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	Solutions of learning problems by Empirical Risk Minimization (ERM) need to be consistent, so that they may be predictive. They also need to be well-posed, so that they can be used robustly. We show that a statistical form of well-posedness, defined in terms of the key property of L-stability, is necessary and sufficient for consistency of ERM.
dc.description	revised July 2003
dc.format	24 p.
dc.format	1854466 bytes
dc.format	400508 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-2002-024
dc.relation	CBCL-223
dc.subject	AI
dc.subject	Theory of Learning
dc.subject	Great Discoveries
dc.subject	Consistency
dc.subject	ERM
dc.subject	Stability
dc.title	Statistical Learning: Stability is Sufficient for Generalization and Necessary and Sufficient for Consistency of Empirical Risk Minimization

Files in this item

Files	Size	Format	View
There are no files associated with this item.