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 14: Random Projection Least Squares (RP LS) algo- rithm from [15] 32 Figure 15: Numerical evidence of δε ALS is an increasing function with respect to residual and leverage
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.