Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms


                Department of Systems Engineering and Engineering Management
                        The Chinese University of Hong Kong


Date: January 27, 2022, Thursday, 8:30 AM


Title: Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms

Speaker: Professor Asu Ozdaglar, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology

We consider a platform's problem of collecting data from privacy sensitive users to estimate an underlying parameter of interest. We formulate this question as a Bayesian-optimal mechanism design problem, in which an individual can share her (verifiable) data in exchange for a monetary reward or services, but at the same time has a (private) heterogeneous privacy sensitivity that represents her cost per unit privacy loss. We consider two popular differential privacy settings for providing privacy guarantees for the users: central and local. In both cases, we establish minimax lower bounds for the estimation error and derive (near) optimal estimators for given heterogeneous privacy loss levels for users. Building on this characterization, we pose the mechanism design problem as the optimal selection of an estimator and payments that will elicit truthful reporting of privacy sensitivities of users under a regularity condition on the distribution of privacy sensitivities, in both privacy settings. Our mechanism in the central setting can be implemented in log-linear time in the number of users, and, in the local setting, it admits a Polynomial Time Approximation Scheme (PTAS).
Joint work with Alireza Fallah, Ali Makhdoumi, and Azarakhsh Malekian.

Asu Ozdaglar received the B.S. degree in electrical engineering from the Middle East Technical University, Ankara, Turkey, in 1996, and the S.M. and the Ph.D. degrees in electrical engineering and computer science from the Massachusetts Institute of Technology, Cambridge, in 1998 and 2003, respectively.
She is the MathWorks Professor of Electrical Engineering and Computer Science in the Electrical Engineering and Computer Science (EECS) Department at the Massachusetts Institute of Technology. She is the department head of EECS and the Deputy Dean of Academics in the Schwarzman College of Computing. Her research expertise includes optimization theory, with emphasis on nonlinear programming and convex analysis, game theory, with applications in communication, social, and economic networks, distributed optimization and control, and network analysis with special emphasis on contagious processes, systemic risk and dynamic control.
Professor Ozdaglar is the recipient of a Microsoft fellowship, the MIT Graduate Student Council Teaching award, the NSF Career award, the 2008 Donald P. Eckman award of the American Automatic Control Council, the Class of 1943 Career Development Chair, the inaugural Steven and Renee Innovation Fellowship, and the 2014 Spira teaching award. She served on the Board of Governors of the Control System Society in 2010 and was an associate editor for IEEE Transactions on Automatic Control. She was the inaugural area co-editor for the area entitled "Games, Information and Networks” in the journal Operations Research. She is the co-author of the book entitled “Convex Analysis and Optimization” (Athena Scientific, 2003).

Enquiries: 3943 8470 (Ms. Elsie Au)

Thursday, January 27, 2022 - 08:30