5 papers
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…
CoinPress: Practical Private Mean and Covariance Estimation
Sourav Biswas, Yihe Dong, Gautam Kamath +1
We present simple differentially private estimators for the mean and covariance of multivariate sub-Gaussian data that are accurate at small sample sizes. We demonstrate the effect…
Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
Xin Gu, Gautam Kamath, Zhiwei Steven Wu
Differentially private stochastic gradient descent privatizes model training by injecting noise into each iteration, where the noise magnitude increases with the number of model pa…
The Discrete Gaussian for Differential Privacy
Clément L. Canonne, Gautam Kamath, Thomas Steinke
A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Unfortunately, using a continuous dist…
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…