COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Mechanism Design via Differential Privacy
FOCS '07 Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science
Neural Network Learning: Theoretical Foundations
Neural Network Learning: Theoretical Foundations
The Limits of Two-Party Differential Privacy
FOCS '10 Proceedings of the 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
Differentially Private Empirical Risk Minimization
The Journal of Machine Learning Research
On the relation between differential privacy and quantitative information flow
ICALP'11 Proceedings of the 38th international conference on Automata, languages and programming - Volume Part II
ICALP'06 Proceedings of the 33rd international conference on Automata, Languages and Programming - Volume Part II
Calibrating noise to sensitivity in private data analysis
TCC'06 Proceedings of the Third conference on Theory of Cryptography
Information-theoretic upper and lower bounds for statistical estimation
IEEE Transactions on Information Theory
Information-Theoretic foundations of differential privacy
FPS'12 Proceedings of the 5th international conference on Foundations and Practice of Security
Hi-index | 0.00 |
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 expected risk under mutual information constraints. We establish 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.