FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift

Federated learning (FL) enables collaborative model training without sharing raw data, but its performance degrades under non-IID data and stochastic client participation. Remedies built on classical Federated Averaging (FedAvg) typically presuppose that client participation probabilities are known to the server, which is rarely the case in deployed systems. We first discuss and then characterize the optimization problem that distributionally agnostic FedAvg actually solves when participation is entirely unknown, possibly highly skewed, and of variable size across rounds: uniform aggregation is shown to minimize a well-defined stochastic objective, weighted by the participation-induced marginal, at a standard O(1/√T) rate for convex and possibly nonsmooth losses. Building on this characterization, we propose Federated Risk-Averse Averaging (textscFedeRage), a risk-averse extension of FedAvg that embeds the Conditional Value-at-Risk (CVaR) into the local objective within a natural distributionally robust optimization (DRO) framework. textscFedeRage implicitly upweights high-loss and infrequently participating clients while adding only a single scalar per-client, and admits an O(kappa/√T) rate in which the factor kappa is the upper bound on the ``price" of risk aversion. In contrast with aggregation-alignment schemes based on optimal transport, which require the availability distribution as an input, textscFedeRage remains agnostic to it. Several experiments on three heterogeneous benchmarks indicate consistent improvements over state-of-the-art methods in accuracy, fairness, and convergence speed.