Rate of convergence of truncated stochastic approximation procedures with moving bounds

Teo Sharia, Lei Zhong

Research output: Contribution to journalArticlepeer-review

31 Downloads (Pure)

Abstract

The paper is concerned with stochastic approximation procedures having three main characteristics: truncations with random moving bounds, a matrix valued random step-size sequence, and a dynamically changing random regression function.We study convergence and rate of convergence. Main results are supplemented with corollaries to establish various sets of sufficient conditions, with the main emphases on the parametric statistical estimation. The theory is illustrated by examples and special cases.
Original languageEnglish
Pages (from-to)262–280
Number of pages19
JournalMathematical Methods of Statistics
Volume25
Issue number4
DOIs
Publication statusPublished - 28 Dec 2016

Cite this