Fang, WenzhiYu, ZiyiJiang, YuningShi, YuanmingJones, Colin N.Zhou, Yong2022-12-052022-12-052022-12-052022-01-0110.1109/TSP.2022.3214122https://infoscience.epfl.ch/handle/20.500.14299/192936WOS:000880643100003Federated learning (FL), as an emerging edge artificial intelligence paradigm, enables many edge devices to collaboratively train a global model without sharing their private data. To enhance the training efficiency of FL, various algorithms have been proposed, ranging from first-order to second-order methods. However, these algorithms cannot be applied in scenarios where the gradient information is not available, e.g., federated black-box attack and federated hyperparameter tuning. To address this issue, in this paper we propose a derivative-free federated zeroth-order optimization (FedZO) algorithm featured by performing multiple local updates based on stochastic gradient estimators in each communication round and enabling partial device participation. Under non-convex settings, we derive the convergence performance of the FedZO algorithm on non-independent and identically distributed data and characterize the impact of the numbers of local iterates and participating edge devices on the convergence. To enable communication-efficient FedZO over wireless networks, we further propose an over-the-air computation (AirComp) assisted FedZO algorithm. With an appropriate transceiver design, we show that the convergence of AirComp-assisted FedZO can still be preserved under certain signal-to-noise ratio conditions. Simulation results demonstrate the effectiveness of the FedZO algorithm and validate the theoretical observations.Engineering, Electrical & ElectronicEngineeringsignal processing algorithmsconvergenceoptimizationatmospheric modelingstochastic processesperformance evaluationtrainingfederated learningzeroth-order optimizationconvergenceover-the-air computationthe-air computationalgorithmsframeworkdesigntext::journal::journal article::research article