Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization

dc.contributor.author Razaviyayn, Mesiam
dc.contributor.author Hong, Mingyi
dc.contributor.author Hong, Mingyi
dc.contributor.author Luo, Zhi-Quan
dc.contributor.author Pang, Jong-Shi
dc.contributor.department Industrial and Manufacturing Systems Engineering
dc.date 2018-02-18T04:45:01.000
dc.date.accessioned 2020-06-30T04:47:01Z
dc.date.available 2020-06-30T04:47:01Z
dc.date.copyright Wed Jan 01 00:00:00 UTC 2014
dc.date.embargo 2017-02-21
dc.date.issued 2014-01-01
dc.description.abstract <p>Consider the problem of minimizing the sum of a smooth (possibly non-convex) and a convex (possibly nonsmooth) function involving a large number of variables. A popular approach to solve this problem is the block coordinate descent (BCD) method whereby at each iteration only one variable block is updated while the remaining variables are held fixed. With the recent advances in the developments of the multi-core parallel processing technology, it is desirable to parallelize the BCD method by allowing multiple blocks to be updated simultaneously at each iteration of the algorithm. In this work, we propose an inexact parallel BCD approach where at each iteration, a subset of the variables is updated in parallel by minimizing convex approximations of the original objective function. We investigate the convergence of this parallel BCD method for both randomized and cyclic variable selection rules. We analyze the asymptotic and non-asymptotic convergence behavior of the algorithm for both convex and non-convex objective functions. The numerical experiments suggest that for a special case of Lasso minimization problem, the cyclic block selection rule can outperform the randomized rule.</p>
dc.description.comments <p>This is a proceeding from the <em>28th Conference on Neural Information Processing Systems </em>(2014). Posted with permission.</p>
dc.format.mimetype application/pdf
dc.identifier archive/lib.dr.iastate.edu/imse_conf/46/
dc.identifier.articleid 1055
dc.identifier.contextkey 9722997
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath imse_conf/46
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/44305
dc.language.iso en
dc.source.bitstream archive/lib.dr.iastate.edu/imse_conf/46/0-NIPS_Permission.pdf|||Sat Jan 15 00:22:32 UTC 2022
dc.source.bitstream archive/lib.dr.iastate.edu/imse_conf/46/2014_Hong_ParallelSuccessive.pdf|||Sat Jan 15 00:22:33 UTC 2022
dc.subject.disciplines Industrial Engineering
dc.subject.disciplines Non-linear Dynamics
dc.subject.disciplines Systems Engineering
dc.title Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization
dc.type article
dc.type.genre conference
dspace.entity.type Publication
relation.isAuthorOfPublication fc95af08-1606-4279-89b3-d787d4df2369
relation.isOrgUnitOfPublication 51d8b1a0-5b93-4ee8-990a-a0e04d3501b1
File
Original bundle
Now showing 1 - 2 of 2
Name:
2014_Hong_ParallelSuccessive.pdf
Size:
338.93 KB
Format:
Adobe Portable Document Format
Description:
Name:
0-NIPS_Permission.pdf
Size:
191.99 KB
Format:
Adobe Portable Document Format
Description: