Dolhare, Harsh ; Borkar, Vivek (2022) A Concentration Bound for Distributed Stochastic Approximation In: 2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 27-30 September 2022, Monticello, IL, USA.
Full text not available from this repository.
Official URL: http://doi.org/10.1109/Allerton49937.2022.9929387
Related URL: http://dx.doi.org/10.1109/Allerton49937.2022.9929387
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.
| Item Type: | Conference or Workshop Item (Other) |
|---|---|
| Source: | Copyright of this article belongs to IEEE. |
| ID Code: | 135127 |
| Deposited On: | 19 Jan 2023 07:25 |
| Last Modified: | 19 Jan 2023 07:25 |
Repository Staff Only: item control page
