Representational Upper Bounds of Bayesian Networks
Abstract
One of the fundamental issues of Bayesian networks is their representational power, reflecting what kind of functions they can or cannot represent. In this paper, we first prove an upper bound on the representational power of Augmented Naive Bayes. We then extend the result to general Bayesian networks. Roughly
Cite
Text
Zhang and Ling. "Representational Upper Bounds of Bayesian Networks." International Conference on Machine Learning, 2002.Markdown
[Zhang and Ling. "Representational Upper Bounds of Bayesian Networks." International Conference on Machine Learning, 2002.](https://mlanthology.org/icml/2002/zhang2002icml-representational/)BibTeX
@inproceedings{zhang2002icml-representational,
title = {{Representational Upper Bounds of Bayesian Networks}},
author = {Zhang, Huajie and Ling, Charles X.},
booktitle = {International Conference on Machine Learning},
year = {2002},
pages = {674-681},
url = {https://mlanthology.org/icml/2002/zhang2002icml-representational/}
}