On expectation propagation for generalised, linear and mixed models

Kim, ASI; Wand, MP

On expectation propagation for generalised, linear and mixed models

Kim, ASI Wand, MP

Permalink

Publication Type:: Journal Article
Citation:: Australian and New Zealand Journal of Statistics, 2018, 60 (1), pp. 75 - 102
Issue Date:: 2018-03-01

Closed Access

	Filename	Description	Size
	Kim_et_al-2018-Australian_&_New_Zealand_Journal_of_Statistics.pdf	Published Version	1.47 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Kim, ASI	en_US
dc.contributor.author	Wand, MP https://orcid.org/0000-0003-2555-896X	en_US
dc.date.issued	2018-03-01	en_US
dc.identifier.citation	Australian and New Zealand Journal of Statistics, 2018, 60 (1), pp. 75 - 102	en_US
dc.identifier.issn	1369-1473	en_US
dc.identifier.uri	http://hdl.handle.net/10453/131710
dc.description.abstract	© 2018 Australian Statistical Publishing Association Inc. Published by John Wiley & Sons Australia Pty Ltd. Expectation propagation is a general approach to deterministic approximate Bayesian inference for graphical models, although its literature is confined mostly to machine learning applications. We investigate the utility of expectation propagation in generalised, linear, and mixed model settings. We show that, even though the algebra and computations are complicated, the notion of message passing on factor graphs affords streamlining of the required calculations and we list the algorithmic steps explicitly. Numerical studies indicate expectation propagation is marginally more accurate than a competing method for the models considered, but at the expense of bigger algebraic and computational overheads.	en_US
dc.relation.ispartof	Australian and New Zealand Journal of Statistics	en_US
dc.relation.isbasedon	10.1111/anzs.12199	en_US
dc.subject.classification	Statistics & Probability	en_US
dc.title	On expectation propagation for generalised, linear and mixed models	en_US
dc.type	Journal Article
utslib.citation.volume	1	en_US
utslib.citation.volume	60	en_US
utslib.for	0104 Statistics	en_US
utslib.for	1403 Econometrics	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	closed_access
pubs.issue	1	en_US
pubs.publication-status	Published	en_US
pubs.volume	60	en_US

Abstract:

© 2018 Australian Statistical Publishing Association Inc. Published by John Wiley & Sons Australia Pty Ltd. Expectation propagation is a general approach to deterministic approximate Bayesian inference for graphical models, although its literature is confined mostly to machine learning applications. We investigate the utility of expectation propagation in generalised, linear, and mixed model settings. We show that, even though the algebra and computations are complicated, the notion of message passing on factor graphs affords streamlining of the required calculations and we list the algorithmic steps explicitly. Numerical studies indicate expectation propagation is marginally more accurate than a competing method for the models considered, but at the expense of bigger algebraic and computational overheads.

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

http://hdl.handle.net/10453/131710