Options
A Concentration Bound for Distributed Stochastic Approximation
Journal
2022 58th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2022
Date Issued
2022-01-01
Author(s)
Dolhare, Harsh
Borkar, Vivek
Abstract
We revisit the classical model of Tsitsiklis, Bertsekas and Athans [10] for distributed stochastic approximation with consensus. The main result is an analysis of this scheme using the 'ODE' (for 'Ordinary Differential Equations') 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.
Subjects