# A Concentration Bound for Distributed Stochastic Approximation

arXiv: https://arxiv.org/abs/2210.04253 · HTML: https://mlsanity.com/paper/2210.04253/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 9 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 3 of 3)

- [Concentration of Contractive Stochastic Approximation and Reinforcement Learning](https://mlsanity.com/paper/2106.14308/) (2021)
- [A Concentration Bound for Stochastic Approximation via Alekseev's Formula](https://mlsanity.com/paper/1506.08657/) (2015)
- [Distributed Stochastic Approximation with Local Projections](https://mlsanity.com/paper/1708.08246/) (2017)

## Abstract (arXiv)

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.