no code implementations • 21 Jan 2022 • Ying Sun, Marie Maros, Gesualdo Scutari, Guang Cheng
Our theory shows that, under standard notions of restricted strong convexity and smoothness of the loss functions, suitable conditions on the network connectivity and algorithm tuning, the distributed algorithm converges globally at a {\it linear} rate to an estimate that is within the centralized {\it statistical precision} of the model, $O(s\log d/N)$.