"Dr. Lian Wen Zhang" wrote:
> Can someone point me to papers on required sample size for
> parameter and structure learning in Bayesian networks?
Stefano Monti 268-7019 writes:
> @Article{dasgup97,
> author = "Sanjoy Dasgupta",
> title = "The Sample Complexity of Learning Fixed-Structure
> {B}ayesian Networks",
> journal = "Machine Learning",
> year = 1997,
> volume = 29,
> number = 2,
> annote = "Bayesian networks; PAC learning; sample complexity"
> }
>
> @InProceedings{friyak96,
> author = "Nir Friedman and Zohar Yakhini",
> title = "On the Sample Complexity of Learning {B}ayesian Networks",
> booktitle = "Proceedings of the 12th Conference of Uncertainty in AI",
> year = 1996
> }
See also
@InProceedings{Hoeffgen-COLT93,
author = "Klaus-U. H{\"o}ffgen",
title = "Learning and Robust Learning of Product Distributions",
pages = "77--83",
booktitle = "Proceedings of the 6th Annual Conference on
Computational Learning Theory",
address = "Santa Cruz, CA, USA",
month = jul,
year = "1993",
publisher = "ACM Press",
}
@InProceedings{LearnBN-UAI97,
Author = "R. Greiner and A. Grove and D. Schuurmans",
title = "Learning {Bayesian} Nets that Perform Well",
booktitle = "Proceedings of the 13th Conference of Uncertainty in AI",
Year = 1997,
}
(Proofs, etc, for the results in the LearnBN-UAI97 (will) appear in
http://www.cs.ualberta.ca/~greiner/BN-results.html#AccurateBN
)
| R Greiner Phone: (780) 492-5461 |
| Dep't of Computing Science FAX: (780) 492-1071 |
| University of Alberta Email: greiner@cs.ualberta.ca |
| Edmonton, AB T6G 2H1 Canada http://www.cs.ualberta.ca/~greiner/ |
This archive was generated by hypermail 2b29 : Wed Sep 27 2000 - 09:09:43 PDT