Partial Order MCMC for Structure Discovery in Bayesian Networks
Teppo Niinimaki, Pekka Parviainen, Mikko Koivisto
We present a new Markov chain Monte Carlo method for estimating posterior probabilities of structural features in Bayesian networks. The method draws samples from the posterior distribution of partial orders on the nodes; for each sampled partial order, the conditional probabilities of interest are computed exactly. We give both analytical and empirical results that suggest the superiority of the new method compared to previous methods, which sample either directed acyclic graphs or linear orders on the nodes.
PDF Link: /papers/11/p557-niinimaki.pdf
AUTHOR = "Teppo Niinimaki
and Pekka Parviainen and Mikko Koivisto",
TITLE = "Partial Order MCMC for Structure Discovery in Bayesian Networks",
BOOKTITLE = "Proceedings of the Twenty-Seventh Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-11)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2011",
PAGES = "557--564"