Flexible Selective Parallel Algorithms for Big Data Optimization

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Flexible Selective Parallel Algorithms for Big Data Optimization

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Flexible Selective Parallel Algorithms for Big Data Optimization

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

CONFERENCE RECORD OF THE 2014 FORTY-EIGHTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS

ISBN

978-1-4799-8297-4

ISSN

1058-6393

e-ISSN

—

Počet stran výsledku

5

Strana od-do

3-7

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Pacific Grove

Datum konání akce

2. 11. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000370964900001