Corpus ID: 18651360

Local Privacy, Data Processing Inequalities, and Statistical Minimax Rates

@article{Duchi2013LocalPD,
  title={Local Privacy, Data Processing Inequalities, and Statistical Minimax Rates},
  author={John C. Duchi and Michael I. Jordan and M. Wainwright},
  journal={arXiv: Statistics Theory},
  year={2013}
}
  • John C. Duchi, Michael I. Jordan, M. Wainwright
  • Published 2013
  • Mathematics, Computer Science
  • arXiv: Statistics Theory
  • Working under a model of privacy in which data remains private even from the statistician, we study the tradeoff between privacy guarantees and the utility of the resulting statistical estimators. We prove bounds on information-theoretic quantities, including mutual information and Kullback-Leibler divergence, that depend on the privacy guarantees. When combined with standard minimax techniques, including the Le Cam, Fano, and Assouad methods, these inequalities allow for a precise… CONTINUE READING
    48 Citations
    Improving Frequency Estimation under Local Differential Privacy
    • 1
    • Highly Influenced
    Privacy-utility tradeoff under statistical uncertainty
    • Ali Makhdoumi, N. Fawaz
    • Computer Science
    • 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton)
    • 2013
    • 49
    • PDF
    Privacy Aware Learning
    • 196
    • PDF
    Discrete Distribution Estimation under Local Privacy
    • 131
    • Highly Influenced
    • PDF
    Locally differentially-private distribution estimation
    • A. Pastore, M. Gastpar
    • Mathematics, Computer Science
    • 2016 IEEE International Symposium on Information Theory (ISIT)
    • 2016
    • 15
    Optimality guarantees for distributed statistical estimation
    • 42
    • PDF

    References

    SHOWING 1-10 OF 65 REFERENCES
    Convergence Rates for Differentially Private Statistical Estimation
    • 43
    • PDF
    Privacy-preserving statistical estimation with optimal convergence rates
    • 206
    • PDF
    The Limits of Two-Party Differential Privacy
    • 156
    • PDF
    Privacy Aware Learning
    • 196
    • PDF
    Lower Bounds in Differential Privacy
    • A. De
    • Computer Science, Mathematics
    • TCC
    • 2012
    • 95
    • PDF
    A Multiplicative Weights Mechanism for Privacy-Preserving Data Analysis
    • M. Hardt, G. N. Rothblum
    • Computer Science
    • 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
    • 2010
    • 328
    • PDF
    On the geometry of differential privacy
    • 287
    • PDF
    Differentially Private Empirical Risk Minimization
    • 787
    • PDF
    Distributed Private Data Analysis: On Simultaneously Solving How and What
    • 135
    • PDF
    A Statistical Framework for Differential Privacy
    • 254
    • PDF