File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Convergence analysis of belief proppagation for pairwise linear Gaussian models

TitleConvergence analysis of belief proppagation for pairwise linear Gaussian models
Authors
Issue Date2017
PublisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1803434
Citation
Proceedings of the fifth IEEE Global Conference on Signal and Information Processing (GlobalSIP), Montreal, Quebec, Canada, 14-16 November 2017, p. 548-552 How to Cite?
AbstractGaussian belief propagation (BP) has been widely used for distributed inference in large-scale networks such as the smart grid, sensor networks, and social networks, where local measurements/observations are scattered over a wide geographical area. One particular case is when two neighboring agents share a common observation. For example, to estimate voltage in the direct current (DC) power flow model, the current measurement over a power line is proportional to the voltage difference between two neighboring buses. When applying the Gaussian BP algorithm to this type of problem, the convergence condition remains an open issue. In this paper, we analyze the convergence properties of Gaussian BP for this pairwise linear Gaussian model. We show analytically that the updating information matrix converges at a geometric rate to a unique positive definite matrix with arbitrary positive semidefinite initial value and further provide the necessary and sufficient convergence condition for the belief mean vector to the optimal estimate.
Persistent Identifierhttp://hdl.handle.net/10722/259707

 

DC FieldValueLanguage
dc.contributor.authorDu, J-
dc.contributor.authorMa, S-
dc.contributor.authorWu, YC-
dc.contributor.authorKar, S-
dc.contributor.authorMoura, J-
dc.date.accessioned2018-09-03T04:12:32Z-
dc.date.available2018-09-03T04:12:32Z-
dc.date.issued2017-
dc.identifier.citationProceedings of the fifth IEEE Global Conference on Signal and Information Processing (GlobalSIP), Montreal, Quebec, Canada, 14-16 November 2017, p. 548-552-
dc.identifier.urihttp://hdl.handle.net/10722/259707-
dc.description.abstractGaussian belief propagation (BP) has been widely used for distributed inference in large-scale networks such as the smart grid, sensor networks, and social networks, where local measurements/observations are scattered over a wide geographical area. One particular case is when two neighboring agents share a common observation. For example, to estimate voltage in the direct current (DC) power flow model, the current measurement over a power line is proportional to the voltage difference between two neighboring buses. When applying the Gaussian BP algorithm to this type of problem, the convergence condition remains an open issue. In this paper, we analyze the convergence properties of Gaussian BP for this pairwise linear Gaussian model. We show analytically that the updating information matrix converges at a geometric rate to a unique positive definite matrix with arbitrary positive semidefinite initial value and further provide the necessary and sufficient convergence condition for the belief mean vector to the optimal estimate.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1803434-
dc.relation.ispartofIEEE Global Conference on Signal and Information Processing (GlobalSIP) Proceedings-
dc.rightsIEEE Global Conference on Signal and Information Processing (GlobalSIP) Proceedings. Copyright © IEEE.-
dc.titleConvergence analysis of belief proppagation for pairwise linear Gaussian models-
dc.typeConference_Paper-
dc.identifier.emailWu, YC: ycwu@eee.hku.hk-
dc.identifier.authorityWu, YC=rp00195-
dc.identifier.doi10.1109/GlobalSIP.2017.8308703-
dc.identifier.hkuros289202-
dc.identifier.spage548-
dc.identifier.epage552-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats