Federated Learning is a collaborative training framework that leverages
...
Stochastic Gradient Descent (SGD) is arguably the most important single
...
In federated learning, a large number of users are involved in a global
...
The celebrated FedAvg algorithm of McMahan et al. (2017) is based on thr...
In this paper, we propose a new zero order optimization method called
mi...
Random Reshuffling (RR), which is a variant of Stochastic Gradient Desce...
We introduce ProxSkip – a surprisingly simple and provably
efficient met...
We present a theoretical study of server-side optimization in federated
...
Virtually all state-of-the-art methods for training supervised machine
l...
We analyze several generic proximal splitting algorithms well suited for...
Most algorithms for solving optimization problems or finding saddle poin...