An Information Theoretic Analysis of Maximum Likelihood Mixture Estimation for Exponential Families (2004)
Cached
Download Links
- [www.aicml.cs.ualberta.ca]
- [www.cs.utexas.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | In Proc. 21st Int. Conf. Machine Learning |
| Citations: | 6 - 4 self |
BibTeX
@INPROCEEDINGS{Banerjee04aninformation,
author = {Arindam Banerjee and Inderjit Dhillon and Joydeep Ghosh and Srujana Merugu},
title = {An Information Theoretic Analysis of Maximum Likelihood Mixture Estimation for Exponential Families},
booktitle = {In Proc. 21st Int. Conf. Machine Learning},
year = {2004},
pages = {2004}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
An important task in unsupervised learning is maximum likelihood mixture estimation (MLME) for exponential families. In this paper, we prove a mathematical equivalence between this MLME problem and the rate distortion problem for Bregman divergences. We also present new theoretical results in rate distortion theory for Bregman divergences. Further, an analysis of the problems as a trade-o between compression and preservation of information is presented that yields the information bottleneck method as an interesting special case.
