… control with unknown gradient statistics: We propose an adaptive power control algorithm
that estimates the gradient statistics based on the historical aggregated gradients and then …

… Statistical heterogeneity refers to the diversity in each user’s data distribution [Li … learn a
strong federated system capable of performing on the global data distribution, although learning …

… over-the-air federated learning over fading channels by taking the gradient distribution into
account. The structure of the optimal power control for SGD learning mainly depends on the …

… Motivated by the above observations, we propose a new federated learning design of
Momentum Federated Learning (MFL) in this paper. In the proposed MFL design, we introduce …

… To generate heterogeneous data that resembles a real federated learning setup, we will
follow a similar approach as in [43]. In this regard, we will distribute the data among clients in a …

… We study a fully decentralized federated learning algorithm, which is a novel gradient … it as
a network gradient descent (NGD) method. In the NGD method, only statistics (eg, parameter …

… design another algorithm, namely Multi-stage Federated Dual Averaging, and prove a high
… Federated Learning (FL) is a popular learning paradigm in distributed learning that enables …

… federated learning (FL) setup where a group of clients periodically coordinate with a central
server to train a statistical … convergence rates under aggressive gradient sparsification, and …

… to learn from extremely large number of devices in federated setting… efficient algorithms for
federated learning with provable … of local Gradient Descent (GD) and local Stochastic Gradient …

… We address the problem of Federated Learning (FL) … a statistical setting with cluster structure.
Another approach is to formulate Federated Learning with non-iid data as a meta learning …