Title :
Rate of convergence analysis of discrete simultaneous perturbation stochastic approximation algorithm
Author :
Qi Wang ; Spall, James C.
Author_Institution :
Dept. of Appl. Math. & Stat., Johns Hopkins Univ., Baltimore, MD, USA
Abstract :
A middle point discrete version of simultaneous perturbation stochastic approximation (DSPSA) algorithm was previously introduced to solve the discrete stochastic optimization problem. We consider the rate of convergence of DSPSA in this paper. This rate will allow for objective comparisons with other discrete stochastic optimization methods.
Keywords :
approximation theory; discrete systems; optimisation; perturbation techniques; stochastic processes; DSPSA algorithm; convergence rate analysis; discrete simultaneous perturbation algorithm; discrete stochastic optimization; stochastic approximation algorithm; Approximation algorithms; Approximation methods; Convergence; Equations; Optimization; Upper bound; Vectors;
Conference_Titel :
American Control Conference (ACC), 2013
Conference_Location :
Washington, DC
Print_ISBN :
978-1-4799-0177-7
DOI :
10.1109/ACC.2013.6580576
