Gaussian mechanism is asymptotically optimal for high-dimensional DP additive noise; new Spherical Generalized Gamma family outperforms it and the ℓ2 mechanism in some low-dimensional cases with tight composition.
Beyond laplace and gaussian: Exploring the generalized gaussian mechanism for private machine learning, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Mixture mechanisms from Gaussians achieve (ε, δ)-DP with substantially lower l1 and l2 noise than the analytic Gaussian mechanism and approach optimality in low-privacy regimes.
citing papers explorer
-
Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy
Gaussian mechanism is asymptotically optimal for high-dimensional DP additive noise; new Spherical Generalized Gamma family outperforms it and the ℓ2 mechanism in some low-dimensional cases with tight composition.
-
Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
Mixture mechanisms from Gaussians achieve (ε, δ)-DP with substantially lower l1 and l2 noise than the analytic Gaussian mechanism and approach optimality in low-privacy regimes.