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.
Beyond laplace and gaussian: Exploring the generalized gaussian mechanism for private machine learning.arXiv:2506.12553,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.