Next Article in Journal
Structural Patterns in Complex Systems Using Multidendrograms
Next Article in Special Issue
The Kalman Filter Revisited Using Maximum Relative Entropy
Previous Article in Journal
Core-Based Dynamic Community Detection in Mobile Social Networks
Previous Article in Special Issue
Objective Bayesianism and the Maximum Entropy Principle
Entropy 2013, 15(12), 5439-5463; doi:10.3390/e15125439
Article

Consistency and Generalization Bounds for Maximum Entropy Density Estimation

1,* , 2
 and 3
1 Kno.e.sis Center, Department of Computer Science and Engineering, Wright State University, Dayton, OH 45435, USA 2 Department of Computing Science, University of Alberta, Edmonton, Alberta T6G 2E8, Canada 3 Visa Inc., San Francisco, CA 94128, USA
* Author to whom correspondence should be addressed.
Received: 9 July 2013 / Revised: 13 November 2013 / Accepted: 3 December 2013 / Published: 9 December 2013
(This article belongs to the Special Issue Maximum Entropy and Bayes Theorem)
Download PDF [318 KB, uploaded 24 February 2015]

Abstract

We investigate the statistical properties of maximum entropy density estimation, both for the complete data case and the incomplete data case. We show that under certain assumptions, the generalization error can be bounded in terms of the complexity of the underlying feature functions. This allows us to establish the universal consistency of maximum entropy density estimation.
Keywords: maximum entropy principle; density estimation; generalization bound; consistency maximum entropy principle; density estimation; generalization bound; consistency
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Share & Cite This Article

Export to BibTeX |
EndNote


MDPI and ACS Style

Wang, S.; Greiner, R.; Wang, S. Consistency and Generalization Bounds for Maximum Entropy Density Estimation. Entropy 2013, 15, 5439-5463.

View more citation formats

Article Metrics

Comments

Citing Articles

[Return to top]
Entropy EISSN 1099-4300 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert