Feb 13, 2013 · Abstract:Working under a model of privacy in which data remains private even from the statistician, we study the tradeoff between privacy ...
scholar.google.com › citations
In this paper, we provide a treatment of two canonical problem families: mean estimation in location family models and convex risk minimization. For these ...
This quantity is the central object of the study in this paper: it characterizes the optimal rate of statistical estimation in terms of the privacy parameter α, ...
People also ask
What is Minimax in statistics?
▻ Non-local notions of privacy? ▻ Privacy without knowing statistical objective? Pre/post-print online: “Local privacy and statistical minimax rates.” D ...
Local privacy and statistical minimax rates. Abstract: We study the tradeoff between privacy guarantees and the utility of statistical estimators under local ...
In this paper, we provide a treatment of two canonical problem families: mean estimation in location family models and convex risk minimization. For these ...
Borders on information-theoretic quantities that influence estimation rates as a function of the amount of privacy preserved can be viewed as quantitative ...
May 26, 2013 · We give sharp minimax rates of convergence for estimation in these locally private settings, exhibiting fundamental tradeoffs between privacy ...
We propose a simple and computationally efficient method, called path thresholding (PaTh), that transforms any tuning parameter-dependent sparse regression ...
We provide a detailed study of the estimation of probability distributions— discrete and continuous—in a stringent setting in which data is kept private ...