Algorithm for stochastic approximation with trial input perturbation in the nonstationary problem of optimization

Authors:
A. T. Vakhitov;O. N. Granichin;L. S. Gurevich
Affiliations:
St. Petersburg State University, St. Petersburg, Russia;St. Petersburg State University, St. Petersburg, Russia;St. Petersburg State University, St. Petersburg, Russia
Venue:
Automation and Remote Control
Year:
2009

Citing 3
Cited 1

Developments in stochastic optimization algorithms with gradient approximations based on function measurements

WSC '94 Proceedings of the 26th conference on Winter simulation
Randomized Algorithms for Stochastic Approximation under Arbitrary Disturbances

Automation and Remote Control
Gradient Methods for Nonstationary Unconstrained Optimization Problems

Automation and Remote Control

Approximate consensus in the dynamic stochastic network with incomplete information and measurement delays

Automation and Remote Control

Quantified Score

Hi-index	0.00

Visualization

Abstract

Consideration was given to the randomized stochastic approximation algorithm with simultaneous trial input perturbation and two measurements used to optimize the unconstrained nonstationary functional. The upper boundary of the mean-square residual was established under conditions of single differentiability of the functional and almost arbitrary noise. Efficiency of the algorithm was illustrated by an example of stabilization of the resulting estimates for the multidimensional case under dependent observation noise.