We consider the problem of learning a model from multiple heterogeneous
...
Recent studies demonstrated that the adversarially robust learning under...
Despite the established convergence theory of Optimistic Gradient Descen...
In this paper we prove that Local (S)GD (or FedAvg) can optimize two-lay...
Local SGD is a promising approach to overcome the communication overhead...
In this paper, we study communication efficient distributed algorithms f...
Investigation of the degree of personalization in federated learning
alg...