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.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7281 |
| Date | 27 January 2004 |
| Creators | Rakhlin, Alexander, Panchenko, Dmitry, Mukherjee, Sayan |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 11 p., 1656004 bytes, 658609 bytes, application/postscript, application/pdf |
| Relation | AIM-2004-001, CBCL-233 |
Page generated in 0.002 seconds