A Concentration Bound for Distributed Stochastic Approximation
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- October 2022
- DOI:
- arXiv:
- arXiv:2210.04253
- Bibcode:
- 2022arXiv221004253D
- Keywords:
-
- Statistics - Machine Learning;
- Computer Science - Machine Learning;
- Mathematics - Probability