Stochastic approximation search algorithms with randomization at the input

Stochastic approximation search algorithms with randomization at the input

0.00 Avg rating0 Votes
Article ID: iaor201526047
Volume: 76
Issue: 5
Start Page Number: 762
End Page Number: 775
Publication Date: May 2015
Journal: Automation and Remote Control
Authors:
Keywords: control, stochastic processes, gradient methods
Abstract:

This work presents a comprehensive survey of the development of pseudogradient stochastic approximation algorithms with randomized input disturbance, considers the problems of their applicability in optimization problems with linear constraints, and discusses new possibilities to use them for multiagent control for load balancing of nodes in computational networks. Justifications of the algorithms’ correctness and their optimal convergence rate are based on the foundational works of B.T. Polyak.

Reviews

Required fields are marked *. Your email address will not be published.