A Concentration Bound for Distributed Stochastic Approximation
Machine Learning
2022-10-11 v1 Machine Learning
Probability
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.
Cite
@article{arxiv.2210.04253,
title = {A Concentration Bound for Distributed Stochastic Approximation},
author = {Harsh Dolhare and Vivek Borkar},
journal= {arXiv preprint arXiv:2210.04253},
year = {2022}
}