Privacy Aware Learning

@article{Duchi2014PrivacyAL,
  title={Privacy Aware Learning},
  author={John C. Duchi and Michael I. Jordan and Martin J. Wainwright},
  journal={J. ACM},
  year={2014},
  volume={61},
  pages={38:1-38:57}
}
  • John C. Duchi, Michael I. Jordan, Martin J. Wainwright
  • Published 2014
  • Computer Science, Mathematics
  • J. ACM
  • We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical estimation procedures. As a consequence, we exhibit a precise tradeoff between the amount of privacy the data preserves and the utility, as measured by convergence rate, of any statistical estimator or learning procedure. 

    Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 153 CITATIONS

    Local privacy and statistical minimax rates

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Regularized Loss Minimizers with Local Data Obfuscation

    VIEW 1 EXCERPT
    CITES BACKGROUND

    User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    The Complexity of Differential Privacy

    • Salil P. Vadhan
    • Computer Science
    • Tutorials on the Foundations of Cryptography
    • 2017
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Corrupt Bandits for Preserving Local Privacy

    VIEW 3 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Development and Analysis of Deterministic Privacy-Preserving Policies Using Non- Stochastic Information Theory

    • Farhad Farokhi
    • Computer Science, Mathematics
    • IEEE Transactions on Information Forensics and Security
    • 2019

    FILTER CITATIONS BY YEAR

    2013
    2020

    CITATION STATISTICS

    • 12 Highly Influenced Citations

    • Averaged 31 Citations per year from 2017 through 2019

    • 58% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 16 REFERENCES

    Differential privacy and robust statistics

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Differentially Private Empirical Risk Minimization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Robust Stochastic Approximation Approach to Stochastic Programming

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Privacy-preserving statistical estimation with optimal convergence rates

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Differential Privacy: A Survey of Results

    VIEW 16 EXCERPTS
    HIGHLY INFLUENTIAL

    Convex Optimization

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Assouad

    • B. Yu
    • Fano, and Le Cam. In Festschrift for Lucien Le Cam, p. 423–435. Springer-Verlag
    • 1997
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL