When machine unlearning jeopardizes privacy
The right to be forgotten states that a data owner has the right to erase their data from an
entity storing it. In the context of machine learning (ML), the right to be forgotten requires an …
entity storing it. In the context of machine learning (ML), the right to be forgotten requires an …
Differential privacy and robust statistics in high dimensions
We introduce a universal framework for characterizing the statistical efficiency of a statistical
estimation problem with differential privacy guarantees. Our framework, which we call High …
estimation problem with differential privacy guarantees. Our framework, which we call High …
The cost of privacy: Optimal rates of convergence for parameter estimation with differential privacy
The cost of privacy: Optimal rates of convergence for parameter estimation with differential
privacy Page 1 The Annals of Statistics 2021, Vol. 49, No. 5, 2825–2850 https://doi.org/10.1214/21-AOS2058 …
privacy Page 1 The Annals of Statistics 2021, Vol. 49, No. 5, 2825–2850 https://doi.org/10.1214/21-AOS2058 …
Efficient mean estimation with pure differential privacy via a sum-of-squares exponential mechanism
We give the first polynomial-time algorithm to estimate the mean of ad-variate probability
distribution with bounded covariance from Õ (d) independent samples subject to pure …
distribution with bounded covariance from Õ (d) independent samples subject to pure …
Private robust estimation by stabilizing convex relaxations
P Kothari, P Manurangsi… - Conference on Learning …, 2022 - proceedings.mlr.press
We give the first polynomial time and sample (epsilon, delta)-differentially private (DP)
algorithm to estimate the mean, covariance and higher moments in the presence of a …
algorithm to estimate the mean, covariance and higher moments in the presence of a …
Robust and differentially private mean estimation
In statistical learning and analysis from shared data, which is increasingly widely adopted in
platforms such as federated learning and meta-learning, there are two major concerns …
platforms such as federated learning and meta-learning, there are two major concerns …
Private and polynomial time algorithms for learning Gaussians and beyond
H Ashtiani, C Liaw - Conference on Learning Theory, 2022 - proceedings.mlr.press
We present a fairly general framework for reducing $(\varepsilon,\delta) $-differentially
private (DP) statistical estimation to its non-private counterpart. As the main application of …
private (DP) statistical estimation to its non-private counterpart. As the main application of …
Privately estimating a Gaussian: Efficient, robust, and optimal
In this work, we give efficient algorithms for privately estimating a Gaussian distribution in
both pure and approximate differential privacy (DP) models with optimal dependence on the …
both pure and approximate differential privacy (DP) models with optimal dependence on the …
Private estimation with public data
We initiate the study of differentially private (DP) estimation with access to a small amount of
public data. For private estimation of $ d $-dimensional Gaussians, we assume that the …
public data. For private estimation of $ d $-dimensional Gaussians, we assume that the …
Covariance-aware private mean estimation without private covariance estimation
We present two sample-efficient differentially private mean estimators for $ d $-dimensional
(sub) Gaussian distributions with unknown covariance. Informally, given $ n\gtrsim d/\alpha …
(sub) Gaussian distributions with unknown covariance. Informally, given $ n\gtrsim d/\alpha …