Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • Article
  • Journal of Privacy and Confidentiality

Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM

By: Katrina Ligett, Seth Neel, Aaron Leon Roth, Bo Waggoner and Steven Wu
  • Format:Electronic
ShareBar

Abstract

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, 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 objectives, 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.

Keywords

Differential Privacy; Empirical Risk Minimization; Accuracy First

Citation

Ligett, Katrina, Seth Neel, Aaron Leon Roth, Bo Waggoner, and Steven Wu. "Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM." Journal of Privacy and Confidentiality 9, no. 2 (2019).
  • Read Now

About The Author

Seth Neel

Technology and Operations Management
→More Publications

More from the Authors

    • September 2022 (Revised October 2022)
    • Faculty Research

    Data Privacy in Practice at LinkedIn

    By: Iavor Bojinov, Marco Iansiti and Seth Neel
    • 2022
    • Faculty Research

    Towards the Unification and Robustness of Post hoc Explanation Methods

    By: Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Steven Wu and Himabindu Lakkaraju
    • 2022
    • Faculty Research

    The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective

    By: Satyapriya Krishna, Tessa Han, Alex Gu, Javin Pombra, Shahin Jabbari, Steven Wu and Himabindu Lakkaraju
More from the Authors
  • Data Privacy in Practice at LinkedIn By: Iavor Bojinov, Marco Iansiti and Seth Neel
  • Towards the Unification and Robustness of Post hoc Explanation Methods By: Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Steven Wu and Himabindu Lakkaraju
  • The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective By: Satyapriya Krishna, Tessa Han, Alex Gu, Javin Pombra, Shahin Jabbari, Steven Wu and Himabindu Lakkaraju
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College