Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
Reads0
Chats0
TLDR
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 that can be significantly more efficient than the standard algorithms in large-dimensional problems.Abstract:
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. >read more
Citations
More filters
W–SPSA in Practice: Approximation of Weight Matrices and Calibration of Traffic Simulation Models
TL;DR: W-S PSA is presented in a formally comprehensive way, where effectively SPSA becomes an instance of W-SPSA, and alternative approaches for determining the matrix W are explored, and it is demonstrated that, relying on a few simplifications that marginally affect the final solution, the authors can obtain W matrices that considerably outperform S PSA.
Proceedings Article
A Learning Analog Neural Network Chip with Continuous-Time Recurrent Dynamics
TL;DR: Experimental results on supervised learning of dynamical features in an analog VLSI neural network chip that implements a stochastic perturbative algorithm and provides for teacher forcing and long-term storage of the volatile parameters.
Journal ArticleDOI
Proportional damping approximation using the energy gain and simultaneous perturbation stochastic approximation
TL;DR: In this paper, the design of vector second-order linear systems for accurate proportional damping approximation is addressed, where an error system is defined using the difference between the generalized coordinates of the non-proportionally damped system and its proportionally damp approximation in modal space.
Journal ArticleDOI
Simultaneous perturbation stochastic approximation of nonsmooth functions
TL;DR: The calculus of the stochastic gradient by means of this presentation and likelihood ratios method is proposed, that can be applied to create SPSA algorithms for a wide class of perturbation densities.
Journal ArticleDOI
Hardware Implementation of a Pulse Density Neural Network Using Simultaneous Perturbation Learning Rule
TL;DR: A combina- tion of the simultaneous perturbation learning rule and the pulse density system results in an interesting architec- ture of hardware neural systems.
References
More filters
Journal ArticleDOI
An Introduction to Probability Theory and Its Applications.
Journal ArticleDOI
Stochastic Estimation of the Maximum of a Regression Function
J. Kiefer,Jacob Wolfowitz +1 more
TL;DR: In this article, the authors give a scheme whereby, starting from an arbitrary point, one obtains successively $x_2, x_3, \cdots$ such that the regression function converges to the unknown point in probability as n \rightarrow \infty.
Journal ArticleDOI
Multidimensional Stochastic Approximation Methods
TL;DR: In this paper, a multidimensional stochastic approximation scheme is presented, and conditions are given for these schemes to converge a.s.p.s to the solutions of $k-stochastic equations in $k$ unknowns.
Journal ArticleDOI
Accelerated Stochastic Approximation
TL;DR: In this article, the Robbins-Monro procedure and the Kiefer-Wolfowitz procedure are considered, for which the magnitude of the $n$th step depends on the number of changes in sign in $(X_i - X_{i - 1})$ for n = 2, \cdots, n.