Approximate computations for binary Markov random fields and their use in Bayesian models
From MaRDI portal
Publication:2361473
Abstract: Discrete Markov random fields form a natural class of models to represent images and spatial data sets. The use of such models is, however, hampered by a computationally intractable normalising constant. This makes parameter estimation and a fully Bayesian treatment of discrete Markov random fields difficult. We apply approximation theory for pseudo-Boolean functions to binary Markov random fields and construct approximations and upper and lower bounds for the associated computationally intractable normalising constant. As a by-product of this process we also get a partially ordered Markov model approximation of the binary Markov random field. We present numerical examples with both the pairwise interaction Ising model and with higher-order interaction models, showing the quality of our approximations and bounds. We also present simulation examples and one real data example demonstrating how the approximations and bounds can be applied for parameter estimation and to handle a fully-Bayesian model computationally.
Recommendations
- Fully Bayesian binary Markov random field models: prior specification and posterior simulation
- Prior specification of neighbourhood and interaction structure in binary Markov random fields
- scientific article; zbMATH DE number 721881
- Approximate Bayes model selection procedures for Gibbs-Markov random fields
- Construction of binary multi-grid Markov random field prior models from training images
Cites work
- A double Metropolis–Hastings sampler for spatial models with intractable normalizing constants
- ABC likelihood-free methods for model choice in Gibbs random fields
- Advanced Markov chain Monte Carlo methods. Learning from past samples.
- An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants
- Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
- Approximations of pseudo-Boolean functions; applications to game theory
- Efficient recursions for general factorisable models
- Equivalent representations of set functions
- Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
- Exact sampling with coupled Markov chains and applications to statistical mechanics
- Formulas for approximating pseudo-Boolean random variables
- scientific article; zbMATH DE number 3986503 (Why is no real title available?)
- scientific article; zbMATH DE number 15992 (Why is no real title available?)
- scientific article; zbMATH DE number 3513115 (Why is no real title available?)
- scientific article; zbMATH DE number 3249560 (Why is no real title available?)
- scientific article; zbMATH DE number 5180199 (Why is no real title available?)
- Image analysis with partially ordered Markov models.
- Maximum likelihood estimation for spatial models by Markov chain Monte Carlo stochastic approximation
- On estimation in binary autologistic spatial models
- On Russian roulette estimates for Bayesian inference with doubly-intractable likelihoods
- Polynomial-Time Approximation Algorithms for the Ising Model
- Posterior sampling when the normalizing constant is unknown
- Recursive computing and simulation-free inference for general factorizable models
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- Simulating normalizing constants: From importance sampling to bridge sampling to path sampling
- State space and hidden Markov models
- Statistics for spatial data
- Transforms of pseudo-Boolean random variables
Cited in
(7)- A multiple-try Metropolis-Hastings algorithm with tailored proposals
- Prior specification for binary Markov mesh models
- Prior specification of neighbourhood and interaction structure in binary Markov random fields
- Fully Bayesian binary Markov random field models: prior specification and posterior simulation
- Log-determinant relaxation for approximate inference in discrete 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 decomposition theorem for binary Markov random fields
This page was built for publication: Approximate computations for binary Markov random fields and their use in Bayesian models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2361473)
