Nonconvex Federated Composite Optimization With Random Reshuffling and Biased Compression
针对非凸且含非光滑正则项的联邦复合优化问题，提出FedRREF算法，结合误差反馈与随机重排技术，降低计算和通信成本，并证明其收敛速度为O(1/√T)。
This article focuses on nonconvex federated composite optimization (FCO) problem, where the loss function is nonconvex and contains a nonsmooth regularizer. To resolve this problem, we propose FedRREF, a novel federated learning algorithm that integrates error feedback (EF) with the efficient random reshuffling (RR) technique, resulting in lower computation and communication costs. To the best of our knowledge, FedRREF is the first algorithm to consider RR and biased compression simultaneously in federated learning, especially in nonsmooth and nonconvex settings, and it is shown to have a $\mathcal {O}(1/\sqrt {T})$ convergence rate, where $T$ is the number of communication rounds. Finally, the numerical experiments illustrate the validity of the proposed algorithm.