*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Algorithms & Randomness Center (ARC)
Aleksandar Nikolov (Univ. of Toronto)
Monday, August 19, 2019
Klaus 1116 East - 11:00 am
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, 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. We also show that factorization mechanisms are instance optimal in some parameter regimes in the central curator model of differential privacy.
Based on joint work with Alexander Edmonds and Jonathan Ullman
----------------------------------
Videos of recent talks are available at: https://smartech.gatech.edu/handle/1853/46836
Click here to subscribe to the seminar email list: arc-colloq@cc.gatech.edu
