Federated learning (FL) is a collaborative machine learning paradigm, which enables deep learning model training over a large volume of decentralized data residing in mobile devices without accessing clients’ private data. Driven by the ever increasing demand for model training of mobile applications or devices, a vast majority of FL tasks are implemented over wireless fading channels. Due to the time-varying nature of wireless channels, however, random delay occurs in both the uplink and downlink transmissions of FL. How to analyze the overall time consumption of a wireless FL task, or more specifically, a FL’s delay distribution, becomes a challenging but important open problem, especially for delay-sensitive model training. In this paper, we present a unified framework to calculate the approximate delay distributions of FL over arbitrary fading channels. Specifically, saddle point approximation, extreme value theory (EVT), and large deviation theory (LDT) are jointly exploited to find the approximate delay distribution along with its tail distribution, which characterizes the quality-of-service of a wireless FL system. Simulation results will demonstrate that our approximation method achieves a small approximation error, which vanishes with the increase of training accuracy.

中文翻译：

---

基于鞍点近似和大偏差理论的无线联邦学习时延分析


联邦学习 (FL) 是一种协作机器学习范例，可以对移动设备中的大量分散数据进行深度学习模型训练，而无需访问客户的私人数据。在移动应用或设备模型训练需求不断增长的推动下，绝大多数 FL 任务都是通过无线衰落通道实现的。然而，由于无线信道的时变特性，FL的上行链路和下行链路传输都会出现随机延迟。如何分析无线 FL 任务的总体时间消耗，或者更具体地说，FL 的延迟分布，成为一个具有挑战性但重要的开放问题，特别是对于延迟敏感的模型训练。在本文中，我们提出了一个统一的框架来计算任意衰落信道上 FL 的近似延迟分布。具体来说，联合利用鞍点近似、极值理论 (EVT) 和大偏差理论 (LDT) 来找到近似延迟分布及其尾部分布，从而表征无线 FL 系统的服务质量。仿真结果将证明我们的近似方法实现了较小的近似误差，该误差随着训练精度的提高而消失。