Differentially private convex optimization with piecewise affine objectives
Shuo Han, Ufuk Topcu, George Pappas

Citation
Shuo Han, Ufuk Topcu, George Pappas. "Differentially private convex optimization with piecewise affine objectives". IEEE Conference on Decision and Control, 2014.

Abstract
Differential privacy is a recently proposed notion of privacy that provides strong privacy guarantees without any assumptions on the adversary. The paper studies the problem of computing a differentially private solution to convex optimization problems whose objective function is piecewise affine. Such problem is motivated by applications in which the affine functions that define the objective function contain sensitive user information. We propose several privacy preserving mechanisms and provide analysis on the trade-offs between optimality and the level of privacy for these mechanisms. Numerical experiments are also presented to evaluate their performance in practice.

Electronic downloads


Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.
Citation formats  
  • HTML
    Shuo Han, Ufuk Topcu, George Pappas. <a
    href="http://www.terraswarm.org/pubs/285.html"
    >Differentially private convex optimization with
    piecewise affine objectives</a>, IEEE Conference on
    Decision and Control, 2014.
  • Plain text
    Shuo Han, Ufuk Topcu, George Pappas. "Differentially
    private convex optimization with piecewise affine
    objectives". IEEE Conference on Decision and Control,
    2014.
  • BibTeX
    @inproceedings{HanTopcuPappas14_DifferentiallyPrivateConvexOptimizationWithPiecewise,
        author = {Shuo Han and Ufuk Topcu and George Pappas},
        title = {Differentially private convex optimization with
                  piecewise affine objectives},
        booktitle = {IEEE Conference on Decision and Control},
        year = {2014},
        abstract = {Differential privacy is a recently proposed notion
                  of privacy that provides strong privacy guarantees
                  without any assumptions on the adversary. The
                  paper studies the problem of computing a
                  differentially private solution to convex
                  optimization problems whose objective function is
                  piecewise affine. Such problem is motivated by
                  applications in which the affine functions that
                  define the objective function contain sensitive
                  user information. We propose several privacy
                  preserving mechanisms and provide analysis on the
                  trade-offs between optimality and the level of
                  privacy for these mechanisms. Numerical
                  experiments are also presented to evaluate their
                  performance in practice. },
        URL = {http://terraswarm.org/pubs/285.html}
    }
    

Posted by Shuo Han on 21 Mar 2014.

Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.