Corpus ID: 162184072

KNG: The K-Norm Gradient Mechanism

@inproceedings{Reimherr2019KNGTK,
  title={KNG: The K-Norm Gradient Mechanism},
  author={Matthew Reimherr and Jordan Awan},
  booktitle={NeurIPS},
  year={2019}
}
  • Matthew Reimherr, Jordan Awan
  • Published in NeurIPS 2019
  • Computer Science, Mathematics
  • This paper presents a new mechanism for producing sanitized statistical summaries that achieve \emph{differential privacy}, called the \emph{K-Norm Gradient} Mechanism, or KNG. This new approach maintains the strong flexibility of the exponential mechanism, while achieving the powerful utility performance of objective perturbation. KNG starts with an inherent objective function (often an empirical risk), and promotes summaries that are close to minimizing the objective by weighting according to… CONTINUE READING

    Citations

    Publications citing this paper.

    One Step to Efficient Synthetic Data

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 39 REFERENCES

    Private Convex Empirical Risk Minimization and High-dimensional Regression

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A near-optimal algorithm for differentially-private principal components

    VIEW 1 EXCERPT

    Differentially Private Empirical Risk Minimization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL