Differential privacy and robust statistics in high dimensions

X Liu, W Kong, S Oh - Conference on Learning Theory, 2022 - proceedings.mlr.press
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 …

Differentially private contextual linear bandits

R Shariff, O Sheffet - Advances in Neural Information …, 2018 - proceedings.neurips.cc
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 …

DPPro: Differentially private high-dimensional data release via random projection

C Xu, J Ren, Y Zhang, Z Qin… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
Releasing representative data sets without compromising the data privacy has attracted
increasing attention from the database community in recent years. Differential privacy is an …

Accuracy, interpretability, and differential privacy via explainable boosting

H Nori, R Caruana, Z Bu, JH Shen… - … on machine learning, 2021 - proceedings.mlr.press
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 …

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 …

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 …

Differentially private model personalization

P Jain, J Rush, A Smith, S Song… - Advances in neural …, 2021 - proceedings.neurips.cc
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 …

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 …

Dp-pca: Statistically optimal and differentially private pca

X Liu, W Kong, P Jain, S Oh - Advances in neural …, 2022 - proceedings.neurips.cc
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 …

Private alternating least squares: Practical private matrix completion with tighter rates

S Chien, P Jain, W Krichene, S Rendle… - International …, 2021 - proceedings.mlr.press
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 …