Edge Consensus Computing for Heterogeneous Data Sets

Niwa, K; Zhang, G; Bastiaan Kleijn, W

Edge Consensus Computing for Heterogeneous Data Sets

Niwa, K Zhang, G

Bastiaan Kleijn, W

Permalink

Publication Type:: Conference Proceeding
Citation:: 2018 IEEE Statistical Signal Processing Workshop, SSP 2018, 2018, pp. 663 - 667
Issue Date:: 2018-08-29

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted manuscriptAdobe PDF (556.67 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Niwa, K	en_US
dc.contributor.author	Zhang, G https://orcid.org/0000-0003-4521-542X	en_US
dc.contributor.author	Bastiaan Kleijn, W	en_US
dc.date.available	2020-08-31T19:21:39Z
dc.date.issued	2018-08-29	en_US
dc.identifier.citation	2018 IEEE Statistical Signal Processing Workshop, SSP 2018, 2018, pp. 663 - 667	en_US
dc.identifier.isbn	9781538615706	en_US
dc.identifier.uri	http://hdl.handle.net/10453/132978
dc.description.abstract	© 2018 IEEE. Edge consensus computing is a framework to optimize a cost function when distributed nodes have distinct data sets available to them. The primal-dual method of multipliers (PDMM) is an optimization algorithm that forms a consensus among nodes by exchanging latent variables rather than the data sets. PDMM often has a high rate of convergence. However, when the nodes see statistically heterogeneous data sets then the performance of PDMM degrades. To overcome this problem, we propose quadratic PDMM. In this method, the original cost functions are replaced by their quadratic majorization based on the L2 norm to ensure homogeneous convexity among nodes. We describe a method to set its parameters optimally for fast convergence. Our experiments confirm that the proposed quadratic PDMM provides good performance even when the data sets are heterogeneous.	en_US
dc.relation.ispartof	2018 IEEE Statistical Signal Processing Workshop, SSP 2018	en_US
dc.relation.isbasedon	10.1109/SSP.2018.8450777	en_US
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Edge Consensus Computing for Heterogeneous Data Sets	en_US
dc.type	Conference Proceeding
utslib.for	0805 Distributed Computing	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 Engineering and Information Technology
utslib.copyright.status	open_access	*
pubs.publication-status	Published	en_US

Abstract:

© 2018 IEEE. Edge consensus computing is a framework to optimize a cost function when distributed nodes have distinct data sets available to them. The primal-dual method of multipliers (PDMM) is an optimization algorithm that forms a consensus among nodes by exchanging latent variables rather than the data sets. PDMM often has a high rate of convergence. However, when the nodes see statistically heterogeneous data sets then the performance of PDMM degrades. To overcome this problem, we propose quadratic PDMM. In this method, the original cost functions are replaced by their quadratic majorization based on the L2 norm to ensure homogeneous convexity among nodes. We describe a method to set its parameters optimally for fast convergence. Our experiments confirm that the proposed quadratic PDMM provides good performance even when the data sets are heterogeneous.

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

http://hdl.handle.net/10453/132978