Hybrid Random/Deterministic Parallel Algorithms for Convex and Nonconvex Big Data Optimization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00231892" target="_blank" >RIV/68407700:21230/15:00231892 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7113892" target="_blank" >http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7113892</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSP.2015.2436357" target="_blank" >10.1109/TSP.2015.2436357</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Hybrid Random/Deterministic Parallel Algorithms for Convex and Nonconvex 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 (possibly nonseparable), 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 a convex surrogate of the original nonconvex function. To tackle 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 show that on huge-scale problems the proposed hybrid random/deterministic algorithm compares favorably to random and deterministic schemes on both convex and n

Název v anglickém jazyce

Hybrid Random/Deterministic Parallel Algorithms for Convex and Nonconvex 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 (possibly nonseparable), 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 a convex surrogate of the original nonconvex function. To tackle 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 show that on huge-scale problems the proposed hybrid random/deterministic algorithm compares favorably to random and deterministic schemes on both convex and n

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/EE2.3.30.0034" target="_blank" >EE2.3.30.0034: Podpora zkvalitnění týmů výzkumu a vývoje a rozvoj intersektorální mobility na ČVUT v Praze</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název periodika

IEEE Transactions on Signal Processing

ISSN

1053-587X

e-ISSN

—

Svazek periodika

63

Číslo periodika v rámci svazku

15

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

3914-3929

Kód UT WoS článku

000357112300006

EID výsledku v databázi Scopus

2-s2.0-84934290103