Network Gradient Descent Algorithm for Decentralized Federated Learning

We study a fully decentralized federated learning algorithm, which is a novel gradient descent algorithm executed on a communication-based network. For convenience, we refer to it as a network gradient descent (NGD) method. In the NGD method, only statistics (e.g., parameter estimates) need to be co...

Full description

Bibliographic Details

Published in:	Journal of business & economic statistics Vol. 41; no. 3; pp. 806 - 818
Main Authors:	Wu, Shuyuan, Huang, Danyang, Wang, Hansheng
Format:	Journal Article
Language:	English
Published:	Alexandria Taylor & Francis 03.07.2023 Taylor & Francis Ltd
Subjects:	Algorithms Decentralized federated learning Deep learning Distributed system Gradient descent
ISSN:	0735-0015, 1537-2707
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!