论文标题
匹配基于追踪的安排，用于空中联合学习
Matching Pursuit Based Scheduling for Over-the-Air Federated Learning
论文作者
论文摘要
本文通过匹配的追求方法开发了一类低复杂设备调度算法，以用于空中联合学习。该提出的方案紧密跟踪了通过差异编程实现的接近最佳性能，并且基于凸弛豫的众所周知的基准算法极大地超越了众所周知的基准算法。与最先进的方案相比，所提出的方案在系统上构成了较低的计算负载：对于$ k $设备和参数服务器上的$ n $天线，基准的复杂性缩放为$ \ left（n^2 + k \ right）^3 + n^6 $，而提议的方案的复杂性则与$ k^p n^q $ 0 $ 0 <P，而$ k^p n^Q $ 0 <P，Q $ 0 <P，通过CIFAR-10数据集上的数值实验证实了所提出的方案的效率。
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.
