# Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks?

arXiv: https://arxiv.org/abs/2301.11817 · HTML: https://mlsanity.com/paper/2301.11817/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2023.

## Built on by (most cited first, 2 of 2)

- [A2CiD2: Accelerating Asynchronous Communication in Decentralized Deep Learning](https://mlsanity.com/paper/2306.08289/) (2023)
- [From promise to practice: realizing high-performance decentralized training](https://mlsanity.com/paper/2410.11998/) (2024)

## Abstract (arXiv)

We consider decentralized optimization problems where one aims to minimize a sum of convex smooth objective functions distributed between nodes in the network. The links in the network can change from time to time. For the setting when the amount of changes is arbitrary, lower complexity bounds and corresponding optimal algorithms are known, and the consensus acceleration is not possible. However, in practice the magnitude of network changes may be limited. We derive lower communication complexity bounds for several regimes of velocity of networks changes. Moreover, we show how to obtain accelerated communication rates for a certain class of time-varying graphs using a specific consensus algorithm.