Accession Number : ADA185818

Title :   Stochastic Approximation and Large Deviations: General Results for W.p.l. Convergence,

Corporate Author : BROWN UNIV PROVIDENCE RI LEFSCHETZ CENTER FOR DYNAMICAL SYSTEMS

Personal Author(s) : Dupuis, Paul ; Kushner, Harold J

PDF Url : ADA185818

Report Date : Feb 1987

Pagination or Media Count : 65

Abstract : W.p.l. convergence results are obtained for stochastic recursive approximation algorithms under very general conditions. The gain sequence (a sub n) can go to zero very slowly and state-dependent noise, discontinuous dynamical equations and the projected or constrained algorithm are all treated. The basic technique is the theory of large deviations. Prior results obtained via this theory are extended in many directions. Keywords: Local linearization; Errors for tracking systems.

Descriptors :   *APPROXIMATION(MATHEMATICS), *CONVERGENCE, *STOCHASTIC PROCESSES, ALGORITHMS, DYNAMICS, EQUATIONS, GAIN, LINEARITY, RECURSIVE FUNCTIONS, SEQUENCES, THEORY, TRACKING

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE