Risk Bounds for Mixture Density Estimation

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7281

Full metadata record

DC Field	Value	Language
dc.creator	Rakhlin, Alexander	-
dc.creator	Panchenko, Dmitry	-
dc.creator	Mukherjee, Sayan	-
dc.date	2004-10-20T21:05:19Z	-
dc.date	2004-10-20T21:05:19Z	-
dc.date	2004-01-27	-
dc.date.accessioned	2013-10-09T02:48:56Z	-
dc.date.available	2013-10-09T02:48:56Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-2004-001	-
dc.identifier	CBCL-233	-
dc.identifier	http://hdl.handle.net/1721.1/7281	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	In this paper we focus on the problem of estimating a bounded density using a finite combination of densities from a given class. We consider the Maximum Likelihood Procedure (MLE) and the greedy procedure described by Li and Barron. Approximation and estimation bounds are given for the above methods. We extend and improve upon the estimation results of Li and Barron, and in particular prove an $O(\\frac{1}{\\sqrt{n}})$ bound on the estimation error which does not depend on the number of densities in the estimated combination.	-
dc.format	11 p.	-
dc.format	1656004 bytes	-
dc.format	658609 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-2004-001	-
dc.relation	CBCL-233	-
dc.subject	AI	-
dc.subject	density estimation	-
dc.subject	MLE	-
dc.title	Risk Bounds for Mixture Density Estimation	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI