Title :
Stochastic approximation method with gradient averaging for unconstrained problems
Author :
Ruszczynski, Andrzej ; Syski, Wojciech
Author_Institution :
Technical University of Warsaw, Warszawa, Poland
fDate :
12/1/1983 12:00:00 AM
Abstract :
A stochastic approximation algorithm is studied, in which random gradient estimates are averaged by an auxiliary, filter. Convergence of the algorithm is proved under a rather general noise condition. A practical version of the method is described and numerical results are given.
Keywords :
Gradient methods; Lyapunov methods; Stochastic approximation; Approximation algorithms; Approximation methods; Automatic control; Convergence; Costs; Filters; Finite difference methods; Gradient methods; Stochastic processes; Stochastic resonance;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.1983.1103184
