Fully Bayesian Binary Markov Random Field Models: Prior Specification and Posterior Simulation

DOI10.1111/SJOS.12146zbMATH Open1419.62270arXiv1501.04419OpenAlexW1480271781MaRDI QIDQ3460656FDOQ3460656

Håkon Tjelmeland, Petter Arnesen

Publication date: 8 January 2016

Published in: Scandinavian Journal of Statistics (Search for Journal in Brave)

Abstract: We propose a flexible prior model for the parameters of binary Markov random fields (MRF) defined on rectangular lattices and with maximal cliques defined from a template maximal clique. The prior model allows higher-order interactions to be included. We also define a reversible jump Markov chain Monte Carlo (RJMCMC) algorithm to sample from the associated posterior distribution. The number of possible parameters for an MRF with for instance k x l maximal cliques becomes high even for small values of k and l. To get a flexible model which may adapt to the structure of a particular observed image we do not put any absolute restrictions on the parametrisation. Instead we define a parametric form for the MRF where the parameters have interpretation as potentials for the various clique configurations, and limit the effective number of parameters by assigning apriori discrete probabilities for events where groups of parameter values are equal. To run our RJMCMC algorithm we have to cope with the computationally intractable normalising constant of MRFs. For this we adopt a previously defined approximation for binary MRFs, but we also briefly discuss other alternatives. We demonstrate the flexibility of our prior formulation with simulated and real data examples.

Full work available at URL: https://arxiv.org/abs/1501.04419

zbMATH Keywords

reversible jump MCMCIsing modelMarkov random fieldsapproximate inferencehigher-order interactions

Mathematics Subject Classification ID

Bayesian inference (62F15) Multivariate distribution of statistics (62H10) Random fields; image analysis (62M40) Monte Carlo methods (65C05) Random fields (60G60) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Applications of statistics to physics (62P35)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Bayesian computing with INLA: new features
• Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
• Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
• A conjugate prior for discrete hierarchical log-linear models
• Markov chain Monte Carlo model determination for hierarchical and graphical log-linear models
• An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants
• Finite exchangeable sequences
• Exact sampling with coupled Markov chains and applications to statistical mechanics
• Equivalent representations of set functions
• Approximations of pseudo-Boolean functions; applications to game theory
• Image analysis with partially ordered Markov models.
• Markov Random Fields with Higher-order Interactions
• Fully Bayesian Approach to Image Restoration with an Application in Biogeography

Cited In (3)

• Prior specification for binary Markov mesh models
• Prior specification of neighbourhood and interaction structure in binary Markov random fields
• Local structure graph models with higher‐order dependence

This page was built for publication: Fully Bayesian Binary Markov Random Field Models: Prior Specification and Posterior Simulation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3460656)