Special CMX Seminar

Friday May 20, 2022 4:00 PM

The Mathematics of Privacy and Synthetic Data

Speaker: Roman Vershynin, Department of Mathematics / Center for Algorithms, Combinatorics and Optimization, University of California Irvine
Location: Online and In-Person Event

In a world where artificial intelligence and data science become omnipresent, data sharing is increasingly locking horns with data-privacy concerns. Among the main data privacy concepts that have emerged are anonymization and differential privacy. Today, another solution is gaining traction-synthetic data. The goal of synthetic data is to create an as-realistic-as-possible dataset, one that not only maintains the nuances of the original data, but does so without risk of exposing sensitive information. The combination of differential privacy with synthetic data has been suggested as a best-of-both-worlds solution. However, the road to privacy is paved with NP-hard problems. The speaker will present three recent mathematical breakthroughs in the NP-hard challenge of creating synthetic data that come with provable privacy and utility guarantees and doing so computationally efficiently. These efforts draw from a wide range of mathematical concepts, particularly random processes. This is joint work with March Boedihardjo and Thomas Strohmer.

Series CMX Lunch Series

Contact: Jolene Brink at (626)395-2813 jbrink@caltech.edu
For more information visit: http://cmx.caltech.edu/