no code implementations • 30 May 2024 • Sushant Agarwal, Gautam Kamath, Mahbod Majid, Argyris Mouzakis, Rose Silver, Jonathan Ullman
We study differentially private (DP) mean estimation in the case where each person holds multiple samples.
no code implementations • 1 Feb 2024 • Mark Bun, Gautam Kamath, Argyris Mouzakis, Vikrant Singhal
We give an example of a class of distributions that is learnable in total variation distance with a finite number of samples, but not learnable under $(\varepsilon, \delta)$-differential privacy.
no code implementations • 30 Jan 2023 • Gautam Kamath, Argyris Mouzakis, Matthew Regehr, Vikrant Singhal, Thomas Steinke, Jonathan Ullman
The canonical algorithm for differentially private mean estimation is to first clip the samples to a bounded range and then add noise to their empirical mean.
no code implementations • 17 May 2022 • Gautam Kamath, Argyris Mouzakis, Vikrant Singhal
First, we provide tight lower bounds for private covariance estimation of Gaussian distributions.
no code implementations • 8 Nov 2021 • Gautam Kamath, Argyris Mouzakis, Vikrant Singhal, Thomas Steinke, Jonathan Ullman
We give the first polynomial-time, polynomial-sample, differentially private estimator for the mean and covariance of an arbitrary Gaussian distribution $\mathcal{N}(\mu,\Sigma)$ in $\mathbb{R}^d$.