Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples

Mohammad Afzali, Hassan Ashtiani, Christopher Liaw

We study the problem of estimating mixtures of Gaussians under the constraint of differential privacy (DP). Our main result is that $\text{poly}(k,d,1/\alpha ,1/\epsilon ,\log (1/\delta ))$ s…