Traditional approaches to differential privacy assume a fixed privacy requirement ε for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is increasingly deployed in practical settings, it may often be that there is instead a fixed accuracy requirement for a given computation and the data analyst would like to maximize the privacy of the computation subject to the accuracy constraint. This raises the question of how to find and run a maximally private empirical risk minimizer subject to a given accuracy requirement. We propose a general “noise reduction” framework that can apply to a variety of private empirical risk minimization (ERM) algorithms, using them to “search” the space of privacy levels to find the empirically strongest one that meets the accuracy constraint, and incurring only logarithmic overhead in the number of privacy levels searched. The privacy analysis of our algorithm leads naturally to a version of differential privacy where the privacy parameters are dependent on the data, which we term ex-post privacy, and which is related to the recently introduced notion of privacy odometers. We also give an ex-post privacy analysis of the classical AboveThreshold privacy tool, modifying it to allow for queries chosen depending on the database. Finally, we apply our approach to two common objective functions, regularized linear and logistic regression, and empirically compare our noise reduction methods to (i) inverting the theoretical utility guarantees of standard private ERM algorithms and (ii) a stronger empirical baseline based on binary search.
Katrina Ligett (Hebrew University)
Seth Neel (University of Pennsylvania)
PhD student in statistics studying fairness and privacy in learning. Advised by Aaron Roth and Michael Kearns.
Aaron Roth (University of Pennsylvania)
Steven Wu (Microsoft)
More from the Same Authors
2016 Workshop: Adaptive Data Analysis »
Vitaly Feldman · Aaditya Ramdas · Aaron Roth · Adam Smith
2015 Poster: Generalization in Adaptive Data Analysis and Holdout Reuse »
Cynthia Dwork · Vitaly Feldman · Moritz Hardt · Toni Pitassi · Omer Reingold · Aaron Roth
2014 Tutorial: Differential Privacy and Learning: The Tools, The Results, and The Frontier »
2012 Poster: A Simple and Practical Algorithm for Differentially Private Data Release »
Moritz Hardt · Katrina Ligett · Frank McSherry