On the Convergence of FedAvg on Non-IID Data

Li, Xiang; Huang, Kaixuan; Yang, Wenhao; Wang, Shusen; Zhang, Zhihua

doi:10.48550/arxiv.1907.02189

Public

On the Convergence of FedAvg on Non-IID Data

Published in arXiv (Cornell University) • Jul 4, 2019

Authors:

Xiang Li

Kaixuan Huang

Wenhao Yang

Abstract

Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the ...

Subject

Convergence (economics)

Rate of convergence

Computer science

Research Assistant

AI chat, annotations, notes & similar papers

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!