Asynchronous Distributed ADMM for Large-Scale Optimization—Part II: Linear Convergence Analysis and Numerical Performance

dc.contributor.author Chang, Tsung-Hui
dc.contributor.author Lao, Wei-Cheng
dc.contributor.author Hong, Mingyi
dc.contributor.author Hong, Mingyi
dc.contributor.author Wang, Xiangfeng
dc.contributor.department Industrial and Manufacturing Systems Engineering
dc.date 2018-02-18T04:39:23.000
dc.date.accessioned 2020-06-30T04:49:13Z
dc.date.available 2020-06-30T04:49:13Z
dc.date.copyright Fri Jan 01 00:00:00 UTC 2016
dc.date.issued 2016-01-01
dc.description.abstract <p>The alternating direction method of multipliers (ADMM) has been recognized as a versatile approach for solving modern large-scale machine learning and signal processing problems efficiently. When the data size and/or the problem dimension is large, a distributed version of ADMM can be used, which is capable of distributing the computation load and the data set to a network of computing nodes. Unfortunately, a direct synchronous implementation of such algorithm does not scale well with the problem size, as the algorithm speed is limited by the slowest computing nodes. To address this issue, in a companion paper, we have proposed an asynchronous distributed ADMM (AD-ADMM) and studied its worst-case convergence conditions. In this paper, we further the study by characterizing the conditions under which the AD-ADMM achieves linear convergence. Our conditions as well as the resulting linear rates reveal the impact that various algorithm parameters, network delay, and network size have on the algorithm performance. To demonstrate the superior time efficiency of the proposed AD-ADMM, we test the AD-ADMM on a high-performance computer cluster by solving a large-scale logistic regression problem.</p>
dc.description.comments <p>This is a manuscript of an article from <em>IEEE Transactions on Signal Processing</em> 64 (2016): 3131, DOI: <a href="https://doi.org/10.1109/TSP.2016.2537261" target="_blank">10.1109/TSP.2016.2537261</a>. Posted with permission.</p>
dc.format.mimetype application/pdf
dc.identifier archive/lib.dr.iastate.edu/imse_pubs/84/
dc.identifier.articleid 1085
dc.identifier.contextkey 9700491
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath imse_pubs/84
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/44607
dc.language.iso en
dc.source.bitstream archive/lib.dr.iastate.edu/imse_pubs/84/2016_Hong_AsynchronousDistributed.pdf|||Sat Jan 15 02:11:02 UTC 2022
dc.source.uri 10.1109/TSP.2016.2537261
dc.subject.disciplines Industrial Engineering
dc.subject.disciplines Systems Architecture
dc.subject.disciplines Systems Engineering
dc.title Asynchronous Distributed ADMM for Large-Scale Optimization—Part II: Linear Convergence Analysis and Numerical Performance
dc.type article
dc.type.genre article
dspace.entity.type Publication
relation.isAuthorOfPublication fc95af08-1606-4279-89b3-d787d4df2369
relation.isOrgUnitOfPublication 51d8b1a0-5b93-4ee8-990a-a0e04d3501b1
File
Original bundle
Now showing 1 - 1 of 1
Name:
2016_Hong_AsynchronousDistributed.pdf
Size:
451.69 KB
Format:
Adobe Portable Document Format
Description:
Collections