3 papers
cs.DS2026
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…
stat.ML2026
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…
stat.ML2025
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…