4 papers
Robust Statistical Estimators with Bounded Empirical Sensitivity
Valentio Iverson, Gautam Kamath, Argyris Mouzakis +1
We introduce a new measure of robustness for statistical estimators, which we call \emph{empirical sensitivity}. An estimator has bounded empirical sensitivity if, with h…
Not All Learnable Distribution Classes are Privately Learnable
Mark Bun, Gautam Kamath, Argyris Mouzakis +1
We give an example of a class of distributions that is learnable up to constant error in total variation distance with a finite number of samples, but not learnable under $(\vareps…
Optimal Differentially Private Sampling of Unbounded Gaussians
Valentio Iverson, Gautam Kamath, Argyris Mouzakis
We provide the first -sample algorithm for sampling from unbounded Gaussian distributions under the constraint of $\left(\varepsilon, δ\righ…
A Bias-Accuracy-Privacy Trilemma for Statistical Estimation
Gautam Kamath, Argyris Mouzakis, Matthew Regehr +3
Differential privacy (DP) is a rigorous notion of data privacy, used for private statistics. The canonical algorithm for differentially private mean estimation is to first clip the…