Search Results for author:
Found 10 papers, 1 papers with code
Not All Learnable Distribution Classes are Privately Learnable
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.
A Polynomial Time, Pure Differentially Private Estimator for Binary Product Distributions
We present the first $\varepsilon$-differentially private, computationally efficient algorithm that estimates the means of product distributions over $\{0, 1\}^d$ accurately in total-variation distance, whilst attaining the optimal sample complexity to within polylogarithmic factors.
A Bias-Variance-Privacy Trilemma for Statistical Estimation
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.
Private Estimation with Public Data
We initiate the study of differentially private (DP) estimation with access to a small amount of public data.
New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma
First, we provide tight lower bounds for private covariance estimation of Gaussian distributions.
A Private and Computationally-Efficient Estimator for Unbounded Gaussians
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 $\mathbb{R}^d$.
Private Mean Estimation of Heavy-Tailed Distributions
We give new upper and lower bounds on the minimax sample complexity of differentially private mean estimation of distributions with bounded $k$-th moments.
Differentially Private Algorithms for Learning Mixtures of Separated Gaussians
Learning the parameters of Gaussian mixture models is a fundamental and widely studied problem with numerous applications.
Privately Learning High-Dimensional Distributions
We present novel, computationally efficient, and differentially private algorithms for two fundamental high-dimensional learning problems: learning a multivariate Gaussian and learning a product distribution over the Boolean hypercube in total variation distance.
