… to local functions and use primal analysis for convergence proof with a local dissimilarity …
hyper-learning rate η. Using primal convergence analysis, we show the linear convergence rate …

… Generalizing such strategies to the federated learning setting is a non-trivial and open …
best of our knowledge) convergence analysis of federated learning with biased client selection …

… • We provide the convergence analysis of local SGD with periodic averaging for heterogeneous
data … Our convergence analysis improves the convergence rate in [20,28] from O …

… Thus, the network scheduling could largely affect the FL convergence. To figure out the
specific effects, we analyze the convergence rate of FL regarding the joint impact of …

… In Section II, we will introduce the learning … the convergence analysis with a sketch of the
proof while a detailed proof can be found in the appendix. Discussions on the convergence …

… We present novel convergence analyses of the standard Federated Averaging (FEDAVG)
scheme under nonIID datasets, full or partial clients participation, direct model or model …

… of a shared model by multiple individual clients via federated learning (FL). To improve the
… Next, under the assumptions of convexity and connectivity, we provide convergence bounds …

… In [15], the authors developed a federated learning based spiking neural network. However,
most of these existing works [4]–[15] whose goal is to minimize the FL convergence time …

… Section III provides the preliminaries of federated learning and the impact of non-IID data
on FL. In Section IV, the convergence analysis and the proposed weighting algorithm are …

… By taking this into account, we show that the convergence in federated learning can be
vastly improved with an appropriate non-uniform device selection method. We first theoretically …