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 …
Differentially private contextual linear bandits
We study the contextual linear bandit problem, a version of the standard stochastic multi-
armed bandit (MAB) problem where a learner sequentially selects actions to maximize a …
armed bandit (MAB) problem where a learner sequentially selects actions to maximize a …
DPPro: Differentially private high-dimensional data release via random projection
Releasing representative data sets without compromising the data privacy has attracted
increasing attention from the database community in recent years. Differential privacy is an …
increasing attention from the database community in recent years. Differential privacy is an …
Accuracy, interpretability, and differential privacy via explainable boosting
We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent
method for training interpretable ML models, yields state-of-the-art accuracy while protecting …
method for training interpretable ML models, yields state-of-the-art accuracy while protecting …
Differentially private synthetic data: Applied evaluations and enhancements
L Rosenblatt, X Liu, S Pouyanfar, E de Leon… - arXiv preprint arXiv …, 2020 - arxiv.org
Machine learning practitioners frequently seek to leverage the most informative available
data, without violating the data owner's privacy, when building predictive models …
data, without violating the data owner's privacy, when building predictive models …
Differentially private ordinary least squares
O Sheffet - International Conference on Machine Learning, 2017 - proceedings.mlr.press
Linear regression is one of the most prevalent techniques in machine learning; however, it is
also common to use linear regression for its explanatory capabilities rather than label …
also common to use linear regression for its explanatory capabilities rather than label …
Differentially private model personalization
We study personalization of supervised learning with user-level differential privacy.
Consider a setting with many users, each of whom has a training data set drawn from their …
Consider a setting with many users, each of whom has a training data set drawn from their …
Privacy-preserving parametric inference: a case for robust statistics
M Avella-Medina - Journal of the American Statistical Association, 2021 - Taylor & Francis
Differential privacy is a cryptographically motivated approach to privacy that has become a
very active field of research over the last decade in theoretical computer science and …
very active field of research over the last decade in theoretical computer science and …
Dp-pca: Statistically optimal and differentially private pca
We study the canonical statistical task of computing the principal component from iid~ data
under differential privacy. Although extensively studied in literature, existing solutions fall …
under differential privacy. Although extensively studied in literature, existing solutions fall …
Private alternating least squares: Practical private matrix completion with tighter rates
We study the problem of differentially private (DP) matrix completion under user-level
privacy. We design a joint differentially private variant of the popular Alternating-Least …
privacy. We design a joint differentially private variant of the popular Alternating-Least …