Oct. 25, 2008 to Oct. 28, 2008
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/FOCS.2008.27
Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept classes can be learned privately, namely, by an algorithm whose output does not depend too heavily on any one input or specific training example? More precisely, we investigate learning algorithms that satisfy differential privacy, a notion that provides strong confidentiality guarantees in the contexts where aggregate information is released about a database containing sensitive information about individuals.
Database Privacy, Learning Theory, PAC Learning
Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi Nissim, Sofya Raskhodnikova, Adam Smith, "What Can We Learn Privately?", FOCS, 2008, 2013 IEEE 54th Annual Symposium on Foundations of Computer Science, 2013 IEEE 54th Annual Symposium on Foundations of Computer Science 2008, pp. 531-540, doi:10.1109/FOCS.2008.27