Truncated Stochastic Approximation with Moving Bounds: Convergence

Research output: Contribution to journalArticlepeer-review

43 Downloads (Pure)


In this paper we consider a wide class of truncated stochastic approximation procedures.
These procedures have three main characteristics: truncations with random moving bounds,
a matrix valued random step-size sequence, and a dynamically changing random regression function.
We establish convergence and consider several examples to illustrate the results
Original languageEnglish
Pages (from-to)163-179
Number of pages17
JournalStatistical Inference for Stochastic Processes
Early online date7 Mar 2014
Publication statusPublished - Jul 2014

Cite this