
Accession Number : AD0842318
Title : A Decision Theoretic Approach to a Stochastic Approximation Problem.
Descriptive Note : Master's thesis,
Corporate Author : AIR FORCE INST OF TECH WRIGHTPATTERSON AFB OH SCHOOL OF ENGINEERING
Personal Author(s) : Evans, Donald L.
Report Date : DEC 1968
Pagination or Media Count : 41
Abstract : The problem of approximating the root of a linear function with unit slope is investigated. The error random variables are assumed to be independent and identically distributed standard normal random variables. A stochastic approximation procedure is characterized as a sequence of decision functions corresponding to a particular sequence of statistical decision problems. Bayes procedures are characterized and convergence is proved. The harmonic RobbinsMonro procedure is shown to correspond to a sequence of 'natural' decision functions. A more general approximation problem is also considered. (Author)
Descriptors : *DECISION THEORY), (*APPROXIMATION(MATHEMATICS), STOCHASTIC PROCESSES, MEASURE THEORY, CONTROL SYSTEMS, CONVERGENCE, THESES.
Subject Categories : Statistics and Probability
Distribution Statement : APPROVED FOR PUBLIC RELEASE