Provable Reduction in Communication Rounds for Non-Smooth Convex Federated Learning

Abstract

Multiple local steps are key to communication-efficient federated learning. However, theoretical guarantees for such algorithms, without data heterogeneity-bounding assumptions, have been lacking in general non-smooth convex problems. Leveraging projection-efficient optimization methods, we propose FedMLS, a federated learning algorithm with provable improvements from multiple local steps. FedMLS attains an $ϵ$-suboptimal solution in $\mathcal{O}(1/ϵ)$ communication rounds, requiring a total of $\mathcal{O}(1/{ϵ}^2)$ stochastic subgradient oracle calls.