Distributed covariance estimation in Gaussian graphical models

Ami Wiesel*, Alfred O. Hero

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We consider distributed covariance estimation in Gaussian graphical models. A typical motivation is learning the potential functions for inference via belief propagation in large scale networks. The classical approach based on a centralized maximum likelihood principle is infeasible, and suboptimal distributed alternatives which tradeoff performance with communication costs are required. We begin with a natural solution where each node performs independent estimation of its local covariance with its neighbors. We show that these local solutions are consistent, and can be interpreted as a pseudo-likelihood method. Based on this interpretation, we propose to enhance the performance by introducing additional symmetry constraints. We enforce these using the methodology of the Alternating Direction Method of Multipliers. This results in a flexible message passing protocol between neighboring nodes which can be implemented in large scale networks.

Original languageAmerican English
Title of host publication2010 IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2010
Pages193-196
Number of pages4
DOIs
StatePublished - 2010
Event2010 IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2010 - Jerusalem, Israel
Duration: 4 Oct 20107 Oct 2010

Publication series

Name2010 IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2010

Conference

Conference2010 IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2010
Country/TerritoryIsrael
CityJerusalem
Period4/10/107/10/10

Fingerprint

Dive into the research topics of 'Distributed covariance estimation in Gaussian graphical models'. Together they form a unique fingerprint.

Cite this