Learning privately with labeled and unlabeled examples

    SODA, pp. 461-477, 2015.

    Cited by: 21|Bibtex|Views5|Links
    EI

    Abstract:

    A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction of private learners, in which the sample complexity is (generally) higher than what is needed for no...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments