MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • Artificial Intelligence Lab Publications
  • AI Memos (1959 - 2004)
  • View Item
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • Artificial Intelligence Lab Publications
  • AI Memos (1959 - 2004)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Risk Bounds for Mixture Density Estimation

Author(s)
Rakhlin, Alexander; Panchenko, Dmitry; Mukherjee, Sayan
Thumbnail
DownloadAIM-2004-001.ps (1.579Mb)
Additional downloads
AIM-2004-001.pdf (643.1Kb)
Metadata
Show full item record
Abstract
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.
Date issued
2004-01-27
URI
http://hdl.handle.net/1721.1/7281
Other identifiers
AIM-2004-001
CBCL-233
Series/Report no.
AIM-2004-001CBCL-233
Keywords
AI, density estimation, MLE

Collections
  • AI Memos (1959 - 2004)
  • CBCL Memos (1993 - 2004)

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.