论文信息 - Extensions of Kestin's Adaptive Stochastic Approximation Method,

Extensions of Kestin's Adaptive Stochastic Approximation Method,

Abstract : Kestin proposed a method for adjusting the coefficients of a scalar stochastic approximation process, and proved w.p.1. convergence. A family of multidimensional processes for function minimization are treated here. Each method consists of a sequence of trucated one-dimensional procedures of the Kestin type. The methods seem to offer a number of advantages over the usual Kiefer-Wolfowitz procedures, and are more natural analogs of the schemes in common use in deterministic optimization theory. (Author)

H. Kushner | T. Gavin

[1] Roger Fletcher,et al. A Rapidly Convergent Descent Method for Minimization , 1963, Comput. J..

[2] A. Dvoretzky. On Stochastic Approximation , 1956 .

[3] D. Elliott,et al. Applications of a simplified multidimensional stochastic approximation algorithm , 1970 .

[4] H. J. Kushner,et al. Adaptive techniques for the optimization of binary detection systems , 1963 .

[5] A note on the maximum sample excursions of stochastic approximation processes. , 1966 .

[6] D. Sakrison. A Continuous Kiefer-Wolfowitz Procedure for Random Processes , 1964 .

[7] On Convergence of the Kiefer-Wolfowitz Approximation Procedure , 1967 .

[8] J. Doob. Stochastic processes , 1953 .

[9] Harold J. Kushner,et al. A Simple Iterative Procedure for the Identification of the Unknown Parameters of a Linear Time Varying Discrete System , 1963 .

[10] Douglass J. Wilde,et al. Foundations of Optimization. , 1967 .

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