no code implementations • 29 Jun 2022 • Enzo Baccarelli, Michele Scarpiniti, Alireza Momenzadeh, Sima Sarv Ahrabi
The convergence properties of AFAFed under (possibly) non-convex loss functions is guaranteed by a set of new analytical bounds, which formally unveil the impact on the resulting AFAFed convergence rate of a number of Federated Learning (FL) parameters, like, first and second moments of the per-coworker number of consecutive model updates, data skewness, communication packet-loss probability, and maximum/minimum values of the (adaptively tuned) mixing coefficient used for model aggregation.