Presenter: Alessandro Epasto
Monday, September 18th, 2023 11:30
Location: Sala Ciminiera, 5th floor Corso Castelfidardo 34
Clustering is a fundamental unsupervised machine learning problem that lies at the core of several real-world applications. While traditional clustering algorithms have not considered the privacy of the users providing the data, recently private clustering has received significant attention. In this talk I will cover recent research in clustering with differential privacy, a strong notion of privacy guarantee promising plausible deniability for user data. I will mostly cover work on clustering graph data. For graph clustering, I will focus on our recent work (ICML 2023) where we show edge-differentially private hierarchical clustering algorithms with provable approximation guarantees.
Alessandro received a Ph.D. in computer science from Sapienza University of Rome, advised by Professor Alessandro Panconesi. Before joining Google, Alessandro was a postdoc at Brown University advised by Professor Eli Upfal. His research interests include problems in the areas of privacy, clustering, and large scale data analysis.