Convergence probability bounds for stochastic approximation

Abstract

A finite-state model for sequential minimum-mean-<lb>square-error estimation of a random variable in additive noise is<lb>analyzed to determine the dependence of opt imum performance<lb>and structure on the memory size of the estimator. Necessary con-<lb>ditions for determining the structure of the opt imum finite-state<lb>estimator are derived for… (More)
DOI: 10.1109/TIT.1970.1054546

Topics

Figures and Tables

Sorry, we couldn't extract any figures or tables for this paper.

Slides referencing similar topics