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 …
Privacy for free: Posterior sampling and stochastic gradient monte carlo
We consider the problem of Bayesian learning on sensitive datasets and present two simple
but somewhat surprising results that connect Bayesian learning to “differential privacy”, a …
but somewhat surprising results that connect Bayesian learning to “differential privacy”, a …
Fast differentially private matrix factorization
Differentially private collaborative filtering is a challenging task, both in terms of accuracy
and speed. We present a simple algorithm that is provably differentially private, while …
and speed. We present a simple algorithm that is provably differentially private, while …
Data-dependent PAC-Bayes priors via differential privacy
Abstract The Probably Approximately Correct (PAC) Bayes framework (McAllester, 1999)
can incorporate knowledge about the learning algorithm and (data) distribution through the …
can incorporate knowledge about the learning algorithm and (data) distribution through the …
Private-knn: Practical differential privacy for computer vision
With increasing ethical and legal concerns on privacy for deep models in visual recognition,
differential privacy has emerged as a mechanism to disguise membership of sensitive data …
differential privacy has emerged as a mechanism to disguise membership of sensitive data …
Generalized gaussian mechanism for differential privacy
F Liu - IEEE Transactions on Knowledge and Data …, 2018 - ieeexplore.ieee.org
Assessment of disclosure risk is of paramount importance in data privacy research and
applications. The concept of differential privacy (DP) formalizes privacy in probabilistic terms …
applications. The concept of differential privacy (DP) formalizes privacy in probabilistic terms …
Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
YX Wang - arxiv preprint arxiv:1803.02596, 2018 - arxiv.org
We revisit the problem of linear regression under a differential privacy constraint. By
consolidating existing pieces in the literature, we clarify the correct dependence of the …
consolidating existing pieces in the literature, we clarify the correct dependence of the …
Differentially private bayesian linear regression
Linear regression is an important tool across many fields that work with sensitive human-
sourced data. Significant prior work has focused on producing differentially private point …
sourced data. Significant prior work has focused on producing differentially private point …
On the theory and practice of privacy-preserving Bayesian data analysis
Bayesian inference has great promise for the privacy-preserving analysis of sensitive data,
as posterior sampling automatically preserves differential privacy, an algorithmic notion of …
as posterior sampling automatically preserves differential privacy, an algorithmic notion of …
Algorithms for differentially private multi-armed bandits
We present differentially private algorithms for the stochastic Multi-Armed Bandit (MAB)
problem. This is a problem for applications such as adaptive clinical trials, experiment …
problem. This is a problem for applications such as adaptive clinical trials, experiment …