# Decentralized SGD with Over-the-Air Computation

Source: [Decentralized SGD with Over-the-Air Computation](<https://www.sota2.com/research/paper/68fa56c31e209131ce99f763>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T14:20:43.891Z

Authors: Emre Ozfatura, Stefano Rini, Deniz Gunduz

Published: 2020-03-06T15:33:59.000Z

## Abstract

We study the performance of decentralized stochastic gradient descent (DSGD) in a wireless network, where the nodes collaboratively optimize an objective function using their local datasets. Unlike the conventional setting, where the nodes communicate over error-free orthogonal communication links, we assume that transmissions are prone to additive noise and interference.We first consider a point-to-point (P2P) transmission strategy, termed the OAC-P2P scheme, in which the node pairs are scheduled in an orthogonal fashion to minimize interference. Since in the DSGD framework, each node requires a linear combination of the neighboring models at the consensus step, we then propose the OAC-MAC scheme, which utilizes the signal superposition property of the wireless medium to achieve over-the-air computation (OAC). For both schemes, we cast the scheduling problem as a graph coloring problem. We numerically evaluate the performance of these two schemes for the MNIST image classification task under various network conditions. We show that the OAC-MAC scheme attains better convergence performance with a fewer communication rounds.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2003.04216>)

[PDF](<https://arxiv.org/pdf/2003.04216.pdf>)
