… federated learning algorithms, which have general applicability to a wide range of machine
learning … the complete control algorithm for adaptive federated learning, which recomputes τ …

… In this paper, we proposed an adaptive federated learning algorithm that learns a mixture
of local and global models as the personalized model. Motivated by learning theory in domain …

… the adaptive gradient method into federated learning. We propose a faster stochastic adaptive
FL … with a general adaptive matrix. • We provide a convergence analysis framework for our …

… Federated learning is a machine learning training paradigm … However, the implementation
of federated learning in practice … -efficient adaptive gradient methods in federated learning, …

… of federated learning. In addition, we analyze the convergence bound of gradientdescent
based federated learning … , which is formalized as Federated Adaptive Weighting (FedAdp), that …

… lenges, we design a deep reinforcement learning (DRL) based mechanism (Adaptive-B) to
… To the best of our knowledge, we are the first to study the impact of adaptive hyperparameter …

… learning rate and the guarantee of calculation fairness. In addition, the isolating data strategy
in the federated learning … a federated learning scheme combined with the adaptive gradient …

… state, is time-varying during the federated learning process. It is also noted that for … federated
learning suffer an unbearable learning delay. To address these issues, we study adaptive …

… five regular federated learning and five federated optimization approaches, our FedDA
federated … , showing the superior performance of FedDA in federated settings. Compared to the …

… Federated learning (FL) is an attractive distributed learning paradigm supporting real-time
continuous learning and client privacy by default. In most FL approaches, all edge clients are …