解决联邦学习中设备随机参与的收敛问题，无需知道参与概率也能保证效果。
Convergence of Agnostic Federated Averaging
- 提出在非均匀、未知参与概率下仍有效的联邦平均算法优化模型。
- 证明凸损失下收敛速度达标准的 $\mathcal{O}(1/\sqrt{T})$。
- 实验证明其优于传统加权聚合方法，即使已知参与权重也更优。
联邦学习（FL）实现去中心化模型训练，无需集中原始数据。然而实际部署常面临关键挑战：客户端间歇性参与服务器聚合，且参与概率未知，可能带有偏差。现有收敛结果多假设全设备参与，或依赖对参与分布的了解（实际为均匀分布）——这些假设在现实中极少成立。本文刻画了在随机（且可变规模）客户端可用性下，经典无偏联邦平均（FedAvg）算法的优化问题，并严格建立其在凸、可能非光滑损失下的收敛性，达到标准 $\mathcal{O}(1/\sqrt{T})$ 收敛率，其中 $T$ 表示聚合周期。分析首次在一般非均匀随机参与下，为无偏 FedAvg 提供收敛保证，且无需知晓参与分布。我们还通过实证表明，即使服务器已知参与权重，无偏 FedAvg 仍优于常见但次优的加权聚合版本。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。