An LDP online federated learning algorithm with temporally correlated noise achieves a sublinear dynamic regret bound for a class of nonconvex losses, outperforming independent-noise approaches.
Improved differential privacy for SGD via optimal private linear oper- ators on adaptive streams,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Locally Differentially Private Online Federated Learning With Correlated Noise
An LDP online federated learning algorithm with temporally correlated noise achieves a sublinear dynamic regret bound for a class of nonconvex losses, outperforming independent-noise approaches.