Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
James C. Spall · IEEE Transactions on Automatic Control · 1992
The problem of finding a root of the multivariate gradient equation that arises in function minimization is considered. When only noisy measurements of the function are available, a stochastic approximation (SA) algorithm for the general Kiefer-Wolfowitz type is appropriate for estimating the root. The paper presents an SA algorithm that is based on a simultaneous perturbation gradient approximation instead of the standard finite-difference approximation of Keifer-Wolfowitz type procedures. Theory and numerical experience indicate that the algorithm can be significantly more efficient than the standard algorithms in large-dimensional problems.>
Cited by 2,274 works. doi:10.1109/9.119632
Authors
References
- An introduction to probability theory and its applications
- Stochastic Estimation of the Maximum of a Regression Function
- An Introduction to Probability Theory and its Applications.
- Stochastic Approximation Methods for Constrained and Unconstrained Systems
- Encyclopedia of Statistical Sciences.
- Multidimensional Stochastic Approximation Methods
- Accelerated Stochastic Approximation
- Optimizing Methods in Statistics
- On Asymptotic Normality in Stochastic Approximation
- Self-organizing control of stochastic systems