NDIS lemma computes closed-form hockey-stick divergence δ(ε) between arbitrary multivariate Gaussians and is applied to obtain tighter privacy for random projection.
Figure 13: Relative DP Least Square Mechanism MLS Input: A matrix D = [ B, b] ∈ Rn×(d+1), where B ∈ Rn×d and b ∈ Rn
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning
NDIS lemma computes closed-form hockey-stick divergence δ(ε) between arbitrary multivariate Gaussians and is applied to obtain tighter privacy for random projection.