@inproceedings{0a46988e1db047a587f43e2a18211cd2,
title = "FEDERATED STOCHASTIC GRADIENT DESCENT BEGETS SELF-INDUCED MOMENTUM",
abstract = "Federated learning (FL) is an emerging machine learning method that can be applied in mobile edge systems, in which a server and a host of clients collaboratively train a statistical model utilizing the data and computation resources of the clients without directly exposing their privacy-sensitive data. We show that running stochastic gradient descent (SGD) in such a setting can be viewed as adding a momentum-like term to the global aggregation process. Based on this finding, we further analyze the convergence rate of a federated learning system by accounting for the effects of parameter staleness and communication resources. These results advance the understanding of the Federated SGD algorithm, and also forges a link between staleness analysis and federated computing systems, which can be useful for systems designers.",
keywords = "Federated learning, convergence rate, momentum, stochastic gradient descent (SGD)",
author = "Yang, {Howard H.} and Zuozhu Liu and Yaru Fu and Quek, {Tony Q.S.} and Poor, {H. Vincent}",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 ; Conference date: 23-05-2022 Through 27-05-2022",
year = "2022",
doi = "10.1109/ICASSP43922.2022.9746995",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
pages = "9027--9031",
booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",
}