2 papers
cs.LG2023
FedDec: Peer-to-peer Aided Federated Learning
Marina Costantini, Giovanni Neglia, Thrasyvoulos Spyropoulos
Federated learning (FL) has enabled training machine learning models exploiting the data of multiple agents without compromising privacy. However, FL is known to be vulnerable to d…
math.OC2022
Pick your Neighbor: Local Gauss-Southwell Rule for Fast Asynchronous Decentralized Optimization
Marina Costantini, Nikolaos Liakopoulos, Panayotis Mertikopoulos +1
In decentralized optimization environments, each agent in a network of nodes has its own private function , and nodes communicate with their neighbors to cooperatively…