This paper develops a class of low-complexity device scheduling algorithms for over-the-air federated learning via the method of matching pursuit. The proposed scheme tracks closely the close-to-optimal performance achieved by difference-of-convex programming, and outperforms significantly the well-known benchmark algorithms based on convex relaxation. Compared to the state-of-the-art, the proposed scheme poses a drastically lower computational load on the system: For $K$ devices and $N$ antennas at the parameter server, the benchmark complexity scales with $\left(N^2+K\right)^3 + N^6$ while the complexity of the proposed scheme scales with $K^p N^q$ for some $0 < p,q \leq 2$. The efficiency of the proposed scheme is confirmed via numerical experiments on the CIFAR-10 dataset.
翻译:本文开发了一组低复杂设备调度算法, 用于通过匹配追寻方法进行超音速联合学习。 所拟议的办法密切跟踪通过混凝土编程所实现的近最佳性能, 大大优于基于康韦克斯放松的众所周知的基准算法。 与最新技术相比, 所拟议的办法在系统中的计算负荷大大降低: 对于参数服务器上的装置和天线, 以$left( N2+K\right) 3 + N 6 美元为基准复杂度, 而拟议办法尺度的复杂度则以$Kp NQQ美元为单位, 约以0. p, q\leq 2美元为单位。 拟议办法的效率通过CFAR- 10数据集的数字实验得到确认。