ECE Department Seminar: Differentially Private Mean Estimation with Connections to Robustness

Description

Lydia Zakynthinou, an assistant professor in the Johns Hopkins Department of Computer Science and a member of the Johns Hopkins Data Science and AI Institute, will give a talk titled "Differentially Private Mean Estimation with Connections to Robustness" for the Electrical and Computer Engineering Department.

Abstract:

Differential privacy provides a rigorous framework for ensuring that the outputs of data-driven systems do not reveal too much sensitive information about individuals in their input. For statistical estimation, practical private algorithms should ideally combine strong accuracy guarantees, computational efficiency, robustness, and minimal reliance on user-specified assumptions. In this talk, I will present algorithmic techniques for private multivariate estimation that achieve strong error guarantees without requiring prior information about the data, by leveraging robustness against data poisoning attacks. I will highlight the deeper connection between differential privacy and robustness that underlies these results. Finally, I will discuss how this connection also reveals inherent limitations for designing computationally efficient estimators, as well as new directions to overcome them.

This talk is based on the following joint works:

• Covariance-aware private mean estimation without covariance estimation: Brown, Gaboardi, Smith, Ullman, Zakynthinou (NeurIPS 2021)
• From robustness to privacy and back: Asi, Ullman, Zakynthinou (ICML 2023)
• Tukey depth mechanisms for practical private mean estimation: Brown, Zakynthinou (ongoing, 2025)