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.
Our data, ourselves: Privacy via distributed noise generation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
Empirical study of DP transfer learning reveals that larger clipping bounds outperform under tight privacy and cumulative DP noise explains batch-size effects better than existing heuristics.
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.
-
Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
-
On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
Empirical study of DP transfer learning reveals that larger clipping bounds outperform under tight privacy and cumulative DP noise explains batch-size effects better than existing heuristics.