Consistency and Generalization Bounds for Maximum Entropy Density Estimation
- Shaojun Wang, Dept of Computing Science
- Russ Greiner, Dept of Computing Science; PI of AICML
- Shaomin Wang, MIT
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.
Citation
S. Wang, R. Greiner, S. Wang. "Consistency and Generalization Bounds for Maximum Entropy Density Estimation". Entropy, 15(12), pp 5439-5463, December 2013.Keywords: | maximum entropy principle, density estimation, generalization bound, consistency, machine learning |
Category: | In Journal |
Web Links: | Journal URL |
DOI |
BibTeX
@article{Wang+al:13, author = {Shaojun Wang and Russ Greiner and Shaomin Wang}, title = {Consistency and Generalization Bounds for Maximum Entropy Density Estimation}, Volume = "15", Number = "12", Pages = {5439-5463}, journal = {Entropy}, year = 2013, }Last Updated: February 10, 2020
Submitted by Sabina P