DRDM combines DRO and FedDyn-style dynamic regularization to improve worst-case client accuracy in federated learning, with a claimed O(1/T^{3/8}) duality-gap convergence rate.
Advances and open problems in federated learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Distributionally Robust Federated Learning with Client Drift Minimization
DRDM combines DRO and FedDyn-style dynamic regularization to improve worst-case client accuracy in federated learning, with a claimed O(1/T^{3/8}) duality-gap convergence rate.