By the same authors

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

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

Author(s)

Department/unit(s)

Publication details

Title of host publicationProceedings of the Seventeenth Annual Conference on Uncertainty in Artificial Intelligence (UAI--2001)
DatePublished - 1 Aug 2001
Pages16-23
Number of pages8
PublisherMORGAN KAUFMANN PUB INC
Place of PublicationSeattle
EditorsJack Breese, Daphne Koller
Original languageEnglish

Abstract

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.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations