Approximate computations for binary Markov random fields and their use in Bayesian models

DOI10.1007/s11222-016-9685-7zbMath1505.62043arXiv1501.07414OpenAlexW2513344208MaRDI QIDQ2361473

Haakon Michael Austad, Håkon Tjelmeland

Publication date: 30 June 2017

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1501.07414

zbMATH Keywords

Bayesian analysisimage analysisspatial dataapproximate inferencepseudo-Boolean functionsvariable elimination algorithmdiscrete Markov random fields

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Random fields; image analysis (62M40) Bayesian inference (62F15)

Related Items (4)

Prior specification of neighbourhood and interaction structure in binary Markov random fields ⋮ Exact or approximate inference in graphical models: why the choice is dictated by the treewidth, and how variable elimination can be exploited ⋮ A multiple-try Metropolis-Hastings algorithm with tailored proposals ⋮ Prior specification for binary Markov mesh models

Uses Software

• bayess

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
• Formulas for approximating pseudo-Boolean random variables
• Transforms of pseudo-Boolean random variables
• Image analysis with partially ordered Markov models.
• On Russian roulette estimates for Bayesian inference with doubly-intractable likelihoods
• Maximum Likelihood Estimation for Spatial Models by Markov Chain Monte Carlo Stochastic Approximation
• Equivalent Representations of Set Functions
• A double Metropolis–Hastings sampler for spatial models with intractable normalizing constants
• Posterior Sampling When the Normalizing Constant is Unknown
• Polynomial-Time Approximation Algorithms for the Ising Model
• Efficient recursions for general factorisable models
• Advanced Markov Chain Monte Carlo Methods
• Approximations of pseudo-Boolean functions; applications to game theory
• Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
• Exact sampling with coupled Markov chains and applications to statistical mechanics
• Statistics for Spatial Data
• On estimation in binary autologistic spatial models
• Recursive computing and simulation-free inference for general factorizable models
• An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants
• Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
• Simulating normalizing constants: From importance sampling to bridge sampling to path sampling
• ABC likelihood-free methods for model choice in Gibbs random fields

This page was built for publication: Approximate computations for binary Markov random fields and their use in Bayesian models