Title :
A stochastic approximation algorithm for large-dimensional systems in the Kiefer-Wolfowitz setting
Author_Institution :
Appl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA
Abstract :
The author considers the problem of finding a root of the multivariate gradient equation that arises in function maximization. When only noisy measurements of the function are available, a stochastic approximation (SA) algorithm of the general type due to Kiefer and Wolfowitz (1952) is appropriate for estimating the root. An SA algorithm is presented that is based on a simultaneous-perturbation gradient approximation instead of the standard finite-difference approximation of Kiefer-Wolfowitz type procedures. Theory and numerical experience indicate that the algorithm can be significantly more efficient than the standard finite-difference-based algorithms in large-dimensional problems
Keywords :
approximation theory; multidimensional systems; parameter estimation; stochastic processes; Kiefer-Wolfowitz type procedures; function maximization; large-dimensional systems; multivariate gradient equation; noisy measurements; parameter estimation; root; simultaneous-perturbation gradient approximation; stochastic approximation algorithm; Approximation algorithms; Convergence; Equations; Finite difference methods; Laboratories; Physics; Q measurement; Stochastic processes; Stochastic resonance; Stochastic systems;
Conference_Titel :
Decision and Control, 1988., Proceedings of the 27th IEEE Conference on
Conference_Location :
Austin, TX
DOI :
10.1109/CDC.1988.194588
