Multivariate stochastic approximation using a simultaneous perturbation gradient approximation

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. >

[1]  J. Berger,et al.  Empirical Bayes Estimation of Rates in Longitudinal Studies , 1983 .

[2]  V. Fabian.  Stochastic Approximation of Minima with Improved Asymptotic Speed , 1967 .

[3]  M. A. Styblinski,et al.  Experiments in nonconvex optimization: Stochastic approximation with function smoothing and simulated annealing , 1990, Neural Networks.

[4]  Y. Wardi.  A stochastic steepest-descent algorithm , 1988 .

[5]  Xi-Ren Cao.  Convergence of parameter sensitivity estimates in a stochastic experiment , 1984, The 23rd IEEE Conference on Decision and Control.

[6]  H. Kushner,et al.  Extensions of Kestin's Adaptive Stochastic Approximation Method, , 1973 .

[7]  M. Metivier,et al.  Applications of a Kushner and Clark lemma to general classes of stochastic algorithms , 1984, IEEE Trans. Inf. Theory.

[8]  L. Goldstein.  On the choice of step size in the Robbins-Monro procedure , 1988 .

[9]  George N. Saridis,et al.  Self-organizing control of stochastic systems , 1977 .

[10]  J. Spall.  Bayesian error isolation for models of large-scale systems , 1988 .

[11]  R. Laha.  Probability Theory , 1979 .

[12]  Y. Ermoliev.  Stochastic quasigradient methods and their application to system optimization , 1983 .

[13]  V. Fabian.  On Asymptotic Normality in Stochastic Approximation , 1968 .

[14]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[15]  J. Blum.  Multidimensional Stochastic Approximation Methods , 1954 .

[16]  J. Spall,et al.  Stochastic approximation for neural network weight estimation in the control of uncertain nonlinear systems , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[17]  L. Ljung.  Strong Convergence of a Stochastic Approximation Algorithm , 1978 .

[18]  Yu. M. Ermol’ev.  On the method of generalized stochastic gradients and quasi-Féjer sequences , 1969 .

[19]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1951 .

[20]  A. Feuer,et al.  Convergence analysis of smoothed stochastic gradient-type algorithm , 1987 .

[21]  J. Spall.  A stochastic approximation algorithm for large-dimensional systems in the Kiefer-Wolfowitz setting , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[22]  R. Shumway,et al.  Estimation and tests of hypotheses for the initial mean and covariance in the kalman filter model , 1981 .

[23]  On using perturbation analysis to do sensitivity analysis: derivatives vs. differences , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[24]  V. Fabian.  Asymptotically Efficient Stochastic Approximation; The RM Case , 1973 .

[25]  D. Ruppert.  A Newton-Raphson Version of the Multivariate Robbins-Monro Procedure , 1985 .

[26]  H. Kesten.  Accelerated Stochastic Approximation , 1958 .

[27]  Perturbation analysis explained , 1987, 26th IEEE Conference on Decision and Control.

[28]  A. Ruszczynski,et al.  Stochastic approximation method with gradient averaging for unconstrained problems , 1983 .