Review on Parameter Estimation in HMRF

TL;DR

This technical report reviews various methodologies for estimating hyper-parameters in Markov Random Fields and Gaussian Hidden Markov Random Fields, including MCMC, EM, and MAP algorithms, supported by simulations and experiments.

Contribution

It provides a comprehensive overview of parameter estimation techniques in HMRF, including new experimental insights and applications to spatial-temporal models.

Findings

Successful simulation of Ising model data using MH algorithm

Effective hyper-parameter estimation via MCMC with pseudo-likelihood

Parameter estimation in Gaussian HMRF improved through experiments

Abstract

This is a technical report which explores the estimation methodologies on hyper-parameters in Markov Random Field and Gaussian Hidden Markov Random Field. In first section, we briefly investigate a theoretical framework on Metropolis-Hastings algorithm. Next, by using MH algorithm, we simulate the data from Ising model, and study on how hyper-parameter estimation in Ising model is enabled through MCMC algorithm using pseudo-likelihood approximation. Following section deals with an issue on parameters estimation process of Gaussian Hidden Markov Random Field using MAP estimation and EM algorithm, and also discusses problems, found through several experiments. In following section, we expand this idea on estimating parameters in Gaussian Hidden Markov Spatial-Temporal Random Field, and display results on two performed experiments.