标题： 对抗联邦平均的收敛性 显示英文标题

标题： Convergence of Agnostic Federated Averaging

摘要： 联邦学习（FL）使得在不集中原始数据的情况下进行去中心化的模型训练成为可能。 然而，实际的FL部署常常面临一个关键的现实挑战：客户端以随机的方式间歇性地参与服务器聚合，并且其参与概率是未知的，可能是有偏的。 现有的大多数收敛结果要么假设所有设备都参与，要么依赖于对客户端可用性分布的了解（实际上是均匀的）——这些假设在现实中很少成立。 在这项工作中，我们分析了一个优化问题，该问题在随机（且大小不一）的客户端可用性下始终遵循著名的\emph{无偏联邦平均（FedAvg）}算法的随机动态，并严格证明了其在凸的、可能不可微损失函数下的收敛性，达到了标准的阶数$\mathcal{O}(1/\sqrt{T})$，其中$T$表示聚合时间窗口。 我们的分析首次为在一般、非均匀、随机客户端参与情况下，无需参与分布知识的无差别 FedAvg 提供了收敛保证。 我们还通过实验证明，即使在服务器端知道参与权重的情况下，无差别 FedAvg 实际上也优于常见的（次优的）加权聚合 FedAvg 变体。 显示英文摘要

摘要： Federated learning (FL) enables decentralized model training without centralizing raw data. However, practical FL deployments often face a key realistic challenge: Clients participate intermittently in server aggregation and with unknown, possibly biased participation probabilities. Most existing convergence results either assume full-device participation, or rely on knowledge of (in fact uniform) client availability distributions -- assumptions that rarely hold in practice. In this work, we characterize the optimization problem that consistently adheres to the stochastic dynamics of the well-known \emph{agnostic Federated Averaging (FedAvg)} algorithm under random (and variably-sized) client availability, and rigorously establish its convergence for convex, possibly nonsmooth losses, achieving a standard rate of order $\mathcal{O}(1/\sqrt{T})$, where $T$ denotes the aggregation horizon. Our analysis provides the first convergence guarantees for agnostic FedAvg under general, non-uniform, stochastic client participation, without knowledge of the participation distribution. We also empirically demonstrate that agnostic FedAvg in fact outperforms common (and suboptimal) weighted aggregation FedAvg variants, even with server-side knowledge of participation weights.