Loading...
Please wait, while we are loading the content...
Similar Documents
Differentially-private learning and information theory.
| Content Provider | CiteSeerX |
|---|---|
| Author | Mir, Darakhshan |
| Abstract | Using results from PAC-Bayesian bounds in learning theory, we formulate differentially-private learning in an information theoretic framework. This, to our knowledge, is the first such treatment of this increasingly popular notion of data privacy. We examine differential privacy in the PAC-Bayesian framework and through such a treatment examine the relation between differentially-private learning and learning in a scenario where we seek to minimize the expectedriskundermutual informationconstraints. Weestablish a connection between the exponential mechanism, which is the most general differentially private mechanism and the Gibbs estimator encountered in PAC-Bayesian bounds. We discover that the goal of finding a probability distribution that minimizes the so-called PAC-Bayesian bounds (under certain assumptions), leads to the Gibbs estimator which is differentially-private. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Differentially-private Learning Information Theory Gibbs Estimator Pac-bayesian Bound Expectedriskundermutual Informationconstraints Popular Notion Information Theoretic Framework So-called Pac-bayesian Bound Exponential Mechanism Private Mechanism First Treatment Probability Distribution Pac-bayesian Framework Data Privacy Differential Privacy Certain Assumption |
| Content Type | Text |
