Convergence of Agnostic Federated Averaging
By: Herlock, Rahimi, Dionysis Kalogerias
Potential Business Impact:
Helps AI learn from phones without seeing your data.
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.
Similar Papers
Revisit the Stability of Vanilla Federated Learning Under Diverse Conditions
Machine Learning (CS)
Keeps medical data private while training AI.
Client-Centric Federated Adaptive Optimization
Machine Learning (CS)
Helps computers learn together without sharing private data.
Decentralized Federated Averaging via Random Walk
Distributed, Parallel, and Cluster Computing
Trains computers better without sharing private info.