FedNew: A communication-efficient and privacy-preserving Newton-type method for federated learning

A Elgabli, CB Issaid, AS Bedi… - International …, 2022 - proceedings.mlr.press
Newton-type methods are popular in federated learning due to their fast convergence. Still,
they suffer from two main issues, namely: low communication efficiency and low privacy due …
被引用次数：25 相关文章

FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning

A Elgabli, CB Issaid, AS Bedi, K Rajawat… - arXiv preprint arXiv …, 2022 - arxiv.org
Newton-type methods are popular in federated learning due to their fast convergence. Still,
they suffer from two main issues, namely: low communication efficiency and low privacy due …

FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning

A Elgabli, CB Issaid, A Bedi, K Rajawat, M Bennis… - icml.cc
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for
Federated Learning Page 1 FedNew: A Communication-Efficient and Privacy-Preserving …

FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning

A Elgabli, C Ben Issaid, AS Bedi, K Rajawat… - arXiv e …, 2022 - ui.adsabs.harvard.edu
Newton-type methods are popular in federated learning due to their fast convergence. Still,
they suffer from two main issues, namely: low communication efficiency and low privacy due …