[Colloquium] Theory Seminar speaker

[Donna Brooms]

REMINDER:

Department of Mathematics & Computer Science
Combinatorics & Theory Seminar

Tuesday, November 5, 2019
Ryerson 251@ 3:30 pm

Aleksandar Nikolov
University of Toronto

Title: The Power of Factorization Mechanisms in Differential Privacy

Abstract:

A central goal in private data analysis is to estimate statistics about an unknown distribution from a dataset possibly containing sensitive information, so that the privacy of any individual represented in the dataset is preserved. We study this question in the model of non-interactive local differential privacy (LDP), in which every person in the dataset randomizes their own data in order to preserve its privacy, before sending it to a central server. We give a characterization of the minimum number of samples necessary to get an accurate estimates of a given set of statistical queries, as well as a characterization of the sample complexity of agnostic PAC learning in this model. The characterization is tight up polylogarithmic factors for any given set of statistical queries, and, respectively, any given concept class. The characterization is achieved by a simple and efficient instance-optimal (with respect to the queries/concept class) approximate factorization mechanism, i.e. a mechanism that answers the statistical queries by answering a different set of strategy queries, from which the answers to the original queries can be approximately reconstructed. 

Based on joint work with Alexander Edmonds and Jonathan Ullman

Donna Brooms-Blue



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20191105/cb850d6b/attachment.html>