… Since the learning performance improves as more devices participate in the federated
learning aggregation, we formulate a beamforming vector optimization problem that maximizes …

… scheme is proposed, which employs random sampling instead of optimization to determine
the aggregator beamforming vector. Notably, the implementation of the proposed scheme …

… MIMO over-the-air federated learning systems with learning rate optimization. We aim to
minimize the MSE of aggregation by jointly optimizing the beamforming vector and the learning …

… rate for federated learning, we propose a joint device selection and beamforming approach
… selection in distributed federated learning, we further train a support vector machine (SVM) …

… learning performance for distributed federated learning, we shall propose a joint device selection
and receiver beamforming … for federated learning tasks, we further train a support vector …

… These approaches correspond to optimize the transmit coefficient (vector) bk (bk), the
receive beamforming vector m, the scaling factor η, and the passive beamforming vector Θ, or …

… round, where N is the number of receive antennas at the PS side, and mt ∈ Cn denote the
receive beamforming vector at the t-th training round. We assume that the channel coefficients …

… Section II presents the federated learning model and our FL algorithm. Section III provides
the … our approach for joint optimization of device selection and receiver beamforming vector. …

… users’ transmit beamforming and the BS’s receive beamforming to minimize … beamforming
vectors. However, recent studies suggest that exploring alternative communication-learning …

… federated learning model, where the local models are updated by secondorder optimization
methods. We then present the over-theair … an optimal receiver beamforming vector for the …