A Concentration Bound for Distributed Stochastic Approximation

From MaRDI portal


MaRDI QIDQ6413354zbMATH OpenFDO

Authors Harsh Dolhare, Vivek Borkar

Publication date 9 October 2022




Abstract: We revisit the classical model of Tsitsiklis, Bertsekas and Athans for distributed stochastic approximation with consensus. The main result is an analysis of this scheme using the ODE approach to stochastic approximation, leading to a high probability bound for the tracking error between suitably interpolated iterates and the limiting differential equation. Several future directions will also be highlighted.












This page was built for publication: A Concentration Bound for Distributed Stochastic Approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6413354)

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=A_Concentration_Bound_for_Distributed_Stochastic_Approximation&oldid=99526883"
Powered by MediaWiki