A stochastic approximation algorithm for large-dimensional systems in the Kiefer-Wolfowitz setting

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.<<ETX>>

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

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

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

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

[5]  G. Saridis.  Stochastic approximation methods for identification and control--A survey , 1974 .

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

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

[8]  R. Martin,et al.  Small sample behavior of robust stochastic approximation and iterated weighted least squares estimates for location , 1984 .

[9]  J. Spall.  A Stochastic Approximation Technique for Generating Maximum Likelihood Parameter Estimates , 1987, 1987 American Control Conference.

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

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

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

[13]  J. Spall,et al.  An Efficient Multistep Stochastic Approximation Algorithm , 1986, 1986 American Control Conference.

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

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

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

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

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