activity
20212026
most citedImproving the Transient Times for Distributed Stochastic Gradient Methods

5 citations · 6 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Achieving Linear Speedup for Composite Federated Learning

Kun Huang, Shi Pu, Karl Henrik Johansson

This paper proposes FedNMap, a normal map-based method for composite federated learning, where the objective consists of a smooth loss and a possibly nonsmooth regularizer. FedNMap…