A synthetic likelihood approach for intractable markov random fields

Zhu, W; Fan, Y

A synthetic likelihood approach for intractable markov random fields

Zhu, W

Fan, Y

Permalink

Publisher:: SPRINGER HEIDELBERG
Publication Type:: Journal Article
Citation:: Computational Statistics, 2023, 38, (2), pp. 749-777
Issue Date:: 2023-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (3.75 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhu, W https://orcid.org/0000-0002-9736-6062
dc.contributor.author	Fan, Y
dc.date.accessioned	2024-03-24T07:03:19Z
dc.date.available	2024-03-24T07:03:19Z
dc.date.issued	2023-01-01
dc.identifier.citation	Computational Statistics, 2023, 38, (2), pp. 749-777
dc.identifier.issn	0943-4062
dc.identifier.issn	1613-9658
dc.identifier.uri	http://hdl.handle.net/10453/177054
dc.description.abstract	We propose a new scalable method to approximate the intractable likelihood of the Potts model. The method decomposes the original likelihood into products of many low-dimensional conditional terms, and a Monte Carlo method is then proposed to approximate each of the small terms using their corresponding (exact) Multinomial distribution. The resulting tractable synthetic likelihood then serves as an approximation to the true likelihood. The method is scalable with respect to lattice size and can also be used for problems with irregular lattices. We provide theoretical justifications for our approach, and carry out extensive simulation studies, which show that our method performs at least as well as existing methods, whilst providing significant computational savings, up to ten times faster than the current fastest method. Finally, we include three real data applications for illustration.
dc.language	English
dc.publisher	SPRINGER HEIDELBERG
dc.relation.ispartof	Computational Statistics
dc.relation.isbasedon	10.1007/s00180-022-01256-x
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	01 Mathematical Sciences, 08 Information and Computing Sciences
dc.subject.classification	Statistics & Probability
dc.subject.classification	46 Information and computing sciences
dc.subject.classification	49 Mathematical sciences
dc.title	A synthetic likelihood approach for intractable markov random fields
dc.type	Journal Article
utslib.citation.volume	38
utslib.for	01 Mathematical Sciences
utslib.for	08 Information and Computing Sciences
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/DVC (Research)
utslib.copyright.status	open_access	*
pubs.consider-herdc	false
dc.date.updated	2024-03-24T07:03:16Z
pubs.issue	2
pubs.publication-status	Published
pubs.volume	38
utslib.citation.issue	2

Abstract:

We propose a new scalable method to approximate the intractable likelihood of the Potts model. The method decomposes the original likelihood into products of many low-dimensional conditional terms, and a Monte Carlo method is then proposed to approximate each of the small terms using their corresponding (exact) Multinomial distribution. The resulting tractable synthetic likelihood then serves as an approximation to the true likelihood. The method is scalable with respect to lattice size and can also be used for problems with irregular lattices. We provide theoretical justifications for our approach, and carry out extensive simulation studies, which show that our method performs at least as well as existing methods, whilst providing significant computational savings, up to ten times faster than the current fastest method. Finally, we include three real data applications for illustration.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/177054