FedNL: Making Newton-Type Methods Applicable to Federated Learning.

Mher Safaryan Rustem Islamov Xun Qian Peter Richtárik

Published in: ICML (2022)

Keyphrases

computational cost
empirical studies
benchmark datasets
learning systems
preprocessing
inductive learning
learned models
data sets
neural network
learning process
prior knowledge
significant improvement
multi class
supervised learning
learning tasks
discriminative learning