Gradient Tracking for High Dimensional Federated Optimization
Abstract
In this paper, we study the (decentralized) distributed optimization problem with high-dimensional sparse structure. Building upon the FedDA algorithm, we propose a (Decentralized) FedDA-GT algorithm, which combines the \textbf{gradient tracking} technique. It is able to eliminate the heterogeneity among different clients' objective functions while ensuring a dimension-free convergence rate. Compared to the vanilla FedDA approach, (D)FedDA-GT can significantly reduce the communication complexity, from to a more efficient . In cases where strong convexity is applicable, we introduce a multistep mechanism resulting in the Multistep ReFedDA-GT algorithm, a minor modified version of FedDA-GT. This approach achieves an impressive communication complexity of through repeated calls to the ReFedDA-GT algorithm. Finally, we conduct numerical experiments, illustrating that our proposed algorithms enjoy the dual advantage of being dimension-free and heterogeneity-free.
Cite
@article{arxiv.2312.05590,
title = {Gradient Tracking for High Dimensional Federated Optimization},
author = {Jiadong Liang and Yang Peng and Zhihua Zhang},
journal= {arXiv preprint arXiv:2312.05590},
year = {2023}
}