Title :
Formal analysis for practical gain sequence selection in recursive stochastic approximation algorithms
Author_Institution :
Dept. of Appl. Math. & Stat., Johns Hopkins Univ., Baltimore, MD, USA
Abstract :
For many popular stochastic approximation algorithms, such as simultaneous perturbation stochastic approximation method and stochastic gradient method, the practical gain sequence selections are different from the optimal selection, which is theoretically derived from asymptotically performance. We provide formal justification for the reasons why we choose such gain sequence in practice.
Keywords :
approximation theory; gradient methods; recursive estimation; sequences; stochastic processes; formal analysis; perturbation stochastic approximation method; practical gain sequence selection; recursive estimation; recursive stochastic approximation algorithm; stochastic gradient method; Antennas; Bandwidth; Energy storage; Impedance; Q-factor; RLC circuits; Zinc; Practical Gain Sequences; Recursive Estimation; Stochastic Approximation;
Conference_Titel :
Information Sciences and Systems (CISS), 2013 47th Annual Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
978-1-4673-5237-6
Electronic_ISBN :
978-1-4673-5238-3
DOI :
10.1109/CISS.2013.6552320
