A new differentially private winsorized mean estimator is shown to be minimax optimal up to logs and improves subsample-and-aggregate over existing private mean estimators.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improved subsample-and-aggregate via the private modified winsorized mean
A new differentially private winsorized mean estimator is shown to be minimax optimal up to logs and improves subsample-and-aggregate over existing private mean estimators.