Convergence of a Robbins-Monro Algorithm for Recursive Parameter Estimation with Non-Monotone Weights and Multiple Zeroes
Convergence of a Robbins-Monro Algorithm for Recursive Parameter Estimation with Non-Monotone Weights and Multiple Zeroes
RR2001-02
Abstract
Convergence properties are established for the output of a deterministic Robbins-Monro recursion for functions that can have singularities and multiple zeros. Our analysis is built largely on adaptations of lemmas of Fradkov published in Russian. We present versions of these lemmas in English for the first time. A gap in Fradkov’s proof of the final lemma is fixed but only for the scalar case.
Others in Series
Working Paper
Frequency-Dependent Probability Measures for Record Linkage
Frequency-Dependent Probability Measures for Record Linkage
Working Paper
Cell Suppression and Audit Programs used for Economic Magnitude Data
Cell Suppression and Audit Programs used for Economic Magnitude Data
Working Paper
Record Linkage Software and Methods for Merging Administrative Lists
Record Linkage Software and Methods for Merging Administrative Lists
Related Information
WORKING PAPER
Statistical Research Reports and Studies
Page Last Revised - October 28, 2021