DocumentCode :
728051
Title :
Parallel and distributed random coordinate descent method for convex error bound minimization
Author :
Necoara, Ion ; Findeisen, Rolf
Author_Institution :
Autom. Control & Syst. Eng. Dept., Univ. Politeh. Bucharest, Bucharest, Romania
fYear :
2015
fDate :
1-3 July 2015
Firstpage :
527
Lastpage :
532
Abstract :
In this paper we propose a parallel and distributed random (block) coordinate descent method for minimizing the sum of a partially separable smooth convex function and a fully separable non-smooth convex function. In this algorithm the iterate updates are done independently and thus it is suitable for parallel and distributed computing architectures. We prove linear convergence rate for the proposed algorithm on the class of problems satisfying a generalized error bound property. We also show that the theoretical estimates on the convergence rate depend on the number of blocks chosen randomly and a natural measure of separability of the objective function. Numerical simulations are also provided to confirm our theory.
Keywords :
convergence; convex programming; minimisation; numerical analysis; parallel architectures; bound minimization; distributed computing architecture; distributed random coordinate descent method; linear convergence rate; numerical simulation; parallel computing architecture; parallel random coordinate descent method; partially separable smooth convex function; Convergence; Convex functions; Indexes; Linear programming; Minimization; Nickel; Optimization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
American Control Conference (ACC), 2015
Conference_Location :
Chicago, IL
Print_ISBN :
978-1-4799-8685-9
Type :
conf
DOI :
10.1109/ACC.2015.7170789
Filename :
7170789
Link To Document :
بازگشت