Introduces federated differential privacy as an intermediate model between local and central DP and analyzes minimax rates for four statistical tasks under heterogeneity and privacy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Federated Transfer Learning with Differential Privacy
Introduces federated differential privacy as an intermediate model between local and central DP and analyzes minimax rates for four statistical tasks under heterogeneity and privacy.