MLE-induced Likelihood for Markov Random Fields

03/27/2018
by   Jie Liu, et al.
0

Due to the intractable partition function, the exact likelihood function for a Markov random field (MRF), in many situations, can only be approximated. Major approximation approaches include pseudolikelihood and Laplace approximation. In this paper, we propose a novel way of approximating the likelihood function through first approximating the marginal likelihood functions of individual parameters and then reconstructing the joint likelihood function from these marginal likelihood functions. For approximating the marginal likelihood functions, we derive a particular likelihood function from a modified scenario of coin tossing which is useful for capturing how one parameter interacts with the remaining parameters in the likelihood function. For reconstructing the joint likelihood function, we use an appropriate copula to link up these marginal likelihood functions. Numerical investigation suggests the superior performance of our approach. Especially as the size of the MRF increases, both the numerical performance and the computational cost of our approach remain consistently satisfactory, whereas Laplace approximation deteriorates and pseudolikelihood becomes computationally unbearable.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/20/2022

Enhanced Laplace Approximation

The Laplace approximation (LA) has been proposed as a method for approxi...
research
03/11/2019

A synthetic likelihood-based Laplace approximation for efficient design of biological processes

Complex models used to describe biological processes in epidemiology and...
research
02/24/2021

A Hybrid Approximation to the Marginal Likelihood

Computing the marginal likelihood or evidence is one of the core challen...
research
06/26/2023

General adjoint-differentiated Laplace approximation

The hierarchical prior used in Latent Gaussian models (LGMs) induces a p...
research
07/06/2021

Fast, universal estimation of latent variable models using extended variational approximations

Generalized linear latent variable models (GLLVMs) are a class of method...
research
08/30/2023

Scalable Estimation of Probit Models with Crossed Random Effects

Crossed random effects structures arise in many scientific contexts. The...
research
06/27/2012

Bayesian Random Fields: The Bethe-Laplace Approximation

While learning the maximum likelihood value of parameters of an undirect...

Please sign up or login with your details

Forgot password? Click here to reset