Markov Chain Monte Carlo using Tree-Based Priors on Model Structure

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We present a general framework for defining priors on model structure and sampling from the posterior using the Metropolis-Hastings algorithm. The key ideas are that structure priors are defined via a probability tree and that the proposal distribution for the Metropolis-Hastings algorithm is defined using the prior, thereby defining a cheaply computable acceptance probability. We have applied this approach to Bayesian net structure learning using a number of priors and proposal distributions. Our results show that these must be chosen appropriately for this approach to be successful.
Original languageEnglish
Title of host publicationProceedings of the Seventeenth Annual Conference on Uncertainty in Artificial Intelligence (UAI--2001)
EditorsJack Breese, Daphne Koller
Place of PublicationSeattle
Number of pages8
Publication statusPublished - 1 Aug 2001

Cite this