Differentially Private (Gradient) Expectation Maximization Algorithm with Statistical Guarantees

Abstract

(Gradient) Expectation Maximization (EM) is a widely used algorithm for estimating the maximum likelihood of mixture models or incomplete data problems. A major challenge facing this popular technique is how to effectively preserve the privacy of sensitive data. Previous research on this problem has already lead to the discovery of some Differentially Private (DP) algorithms for (Gradient) EM. However, unlike in the non-private case, existing techniques are not yet able to provide finite sample statistical guarantees. To address this issue, we propose in this paper the first DP version of (Gradient) EM algorithm with statistical guarantees. Moreover, we apply our general framework to three canonical models: Gaussian Mixture Model (GMM), Mixture of Regressions Model (MRM) and Linear Regression with Missing Covariates (RMC). Specifically, for GMM in the DP model, our estimation error is near optimal in some cases. For the other two models, we provide the first finite sample statistical guarantees. Our theory is supported by thorough numerical experiments.

arXiv commentSubmiited. arXiv admin note: text overlap with arXiv:2010.09576

References in corpus (6)

• Deep Learning with Differential Privacy
• High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexity
• Regularized EM Algorithms: A Unified Framework and Statistical Guarantees
• Dimension-free PAC-Bayesian bounds for matrices, vectors, and linear least squares regression
• Propose, Test, Release: Differentially private estimation with high probability
• Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient Descent

Cited by in corpus (2)

• Privacy-Preserving Distributed Expectation Maximization for Gaussian Mixture Model using Subspace Perturbation
• High-Dimensional Differentially-Private EM Algorithm: Methods and Near-Optimal Statistical Guarantees