BriefGPT.xyz
Mar, 2022
FedADMM：一种允许部分参与的联合原始对偶算法
FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation
HTML
PDF
Han Wang, Siddartha Marella, James Anderson
TL;DR
该研究提出一种新的联邦学习算法FedADMM，解决具有非光滑正则化器的非凸复合优化问题，以促进通信效率和数据隐私。作者证明了在一般的采样模型下，在不是所有客户端都能参与给定通信轮的情况下，FedADMM会收敛。
Abstract
federated learning
is a framework for distributed optimization that places emphasis on
communication efficiency
. In particular, it follows a client-server broadcast model and is particularly appealing because of
→