On Convergence Analysis of Gradient Based Primal-Dual Method of Multipliers

Zhang, G; Orconnor, M; Li, L

On Convergence Analysis of Gradient Based Primal-Dual Method of Multipliers

Zhang, G

Orconnor, M Li, L

Permalink

Publication Type:: Conference Proceeding
Citation:: 2018 IEEE Statistical Signal Processing Workshop, SSP 2018, 2018, pp. 353 - 357
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 (709.48 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, G https://orcid.org/0000-0003-4521-542X	en_US
dc.contributor.author	Orconnor, M	en_US
dc.contributor.author	Li, L	en_US
dc.date.available	2020-08-30T19:06:52Z
dc.date.issued	2018-08-29	en_US
dc.identifier.citation	2018 IEEE Statistical Signal Processing Workshop, SSP 2018, 2018, pp. 353 - 357	en_US
dc.identifier.isbn	9781538615706	en_US
dc.identifier.uri	http://hdl.handle.net/10453/129720
dc.description.abstract	© 2018 IEEE. Recently, the primal-dual method of multipliers (PDMM) has been proposed and successfully applied to solve a number of decomposable convex optimizations distributedly and iteratively. In this work, we study the gradient based PDMM (GPDMM), where the objective functions are approximated using the gradient information per iteration. It is shown that for a certain class of decomposable convex optimizations, synchronous GPDMM has a sublinear convergence rate of O(1/K) (where K denotes the iteration index). Experiments on a problem of distributed ridge regularized logistic regression demonstrate the efficiency of synchronous GPDMM.	en_US
dc.relation.ispartof	2018 IEEE Statistical Signal Processing Workshop, SSP 2018	en_US
dc.relation.isbasedon	10.1109/SSP.2018.8450854	en_US
dc.rights	info:eu-repo/semantics/openAccess
dc.title	On Convergence Analysis of Gradient Based Primal-Dual Method of Multipliers	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. Recently, the primal-dual method of multipliers (PDMM) has been proposed and successfully applied to solve a number of decomposable convex optimizations distributedly and iteratively. In this work, we study the gradient based PDMM (GPDMM), where the objective functions are approximated using the gradient information per iteration. It is shown that for a certain class of decomposable convex optimizations, synchronous GPDMM has a sublinear convergence rate of O(1/K) (where K denotes the iteration index). Experiments on a problem of distributed ridge regularized logistic regression demonstrate the efficiency of synchronous GPDMM.

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

http://hdl.handle.net/10453/129720