Differentially private synthetic data provide a powerful mechanism to enable data analysis while protecting sensitive information about individuals. We first present a highly effective algorithmic approach for generating differentially private synthetic data in a bounded metric space with near-optimal utility guarantees under the Wasserstein distance. When the data lie in a high-dimensional space, the accuracy of the synthetic data suffers from the curse of dimensionality. We then propose an algorithm to generate low-dimensional private synthetic data efficiently from a high-dimensional dataset. A key step in our algorithm is a private principal component analysis (PCA) procedure with a near-optimal accuracy bound. Based on joint work with Yiyun He (UC Irvine), Roman Vershynin (UC Irvine), and Thomas Strohmer (UC Davis).

9 Aug 2023
10am - 11am
Where
Room 4504 (Lifts 25/26)
Speakers/Performers
Prof. Yizhe ZHU
University of California, Irvine
Organizer(S)
Department of Mathematics
Contact/Enquiries
Payment Details
Audience
Alumni, Faculty and staff, PG students, UG students
Language(s)
English
Other Events
8 Nov 2024
Seminar, Lecture, Talk
IAS / School of Science Joint Lecture - Some Theorems in the Representation Theory of Classical Lie Groups
Abstract After introducing some basic notions in the representation theory of classical Lie groups, the speaker will explain three results in this theory: the multiplicity one theorem for classical...
21 Jun 2024
Seminar, Lecture, Talk
IAS / School of Science Joint Lecture - Alzheimer’s Disease is Likely a Lipid-disorder Complication: an Example of Functional Lipidomics for Biomedical and Biological Research
Abstract Functional lipidomics is a frontier in lipidomics research, which identifies changes of cellular lipidomes in disease by lipidomics, uncovers the molecular mechanism(s) leading to the chan...