Paperlane

no. 16 · Tuesday 17 November 2026

Communication-Efficient Distributionally Robust Federated Averaging with Multi-Source Data

Yingzhu Liu, Zhongkui Li, Pengcheng You and Ashish Cherukuri

math.OC · via cs.LG

Abstract

Federated learning trains a shared model from distributed client data. The deployment risk is typically specified through two approximations: each unknown local distribution is replaced by its empirical distribution, and the unknown deployment mixture across clients is replaced by empirical or prescribed training weights. Existing robust methods usually address one approximation at a time through local distributional ambiguity sets or worst-case client mixtures. However, joint treatment of both approximations remains underexplored. To address this gap, we construct a global ambiguity set formed by admissible mixtures of client-wise Wasserstein ambiguity sets, yielding a distributionally robust optimization formulation. The construction allows client-dependent ambiguity radii, preserves client-wise separability of the objective function, and yields a high-probability out-of-sample guarantee for the resulting robust problem. We then introduce a penalty-based approximation of this formulation and develop a communication-efficient algorithm called BiDRO-FedAvg, for which we establish a convergence guarantee. We validate the proposed framework through a market-demand prediction simulation.

fields
Optimization and Control
pdf ↗ page arXiv:2611.20060 ↗