Flexible Selective Parallel Algorithms for Big Data Optimization
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00310361" target="_blank" >RIV/68407700:21230/14:00310361 - isvavai.cz</a>
Result on the web
<a href="http://ieeexplore.ieee.org/document/7094384/" target="_blank" >http://ieeexplore.ieee.org/document/7094384/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ACSSC.2014.7094384" target="_blank" >10.1109/ACSSC.2014.7094384</a>
Alternative languages
Result language
angličtina
Original language name
Flexible Selective Parallel Algorithms for Big Data Optimization
Original language description
We propose a decomposition framework for the parallel optimization of the sum of a differentiable (possibly nonconvex) function and a nonsmooth (separable), convex one. The latter term is usually employed to enforce structure in the solution, typically sparsity. The main contribution of this work is a novel parallel, hybrid random/deterministic decomposition scheme wherein, at each iteration, a subset of (block) variables is updated at the same time by minimizing local convex approximations of the original nonconvex function. To tackle with huge-scale problems, the (block) variables to be updated are chosen according to a mixed random and deterministic procedure, which captures the advantages of both pure deterministic and random update-based schemes. Almost sure convergence of the proposed scheme is established. Numerical results on huge-scale problems show that the proposed algorithm outperforms current schemes.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JC - Computer hardware and software
OECD FORD branch
—
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
CONFERENCE RECORD OF THE 2014 FORTY-EIGHTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS
ISBN
978-1-4799-8297-4
ISSN
1058-6393
e-ISSN
—
Number of pages
5
Pages from-to
3-7
Publisher name
IEEE Computer Society
Place of publication
USA
Event location
Pacific Grove
Event date
Nov 2, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000370964900001