Lydia Zakynthinou

About

I am an assistant professor in the Department of Computer Science at Johns Hopkins University.

Before that, I was a FODSI-Simons postdoctoral research fellow at UC Berkeley, hosted by Michael Jordan. I completed my PhD at the Khoury College of Computer Sciences at Northeastern University, where I was fortunate to be advised by Huy Lê Nguyễn and Jonathan Ullman. My PhD research (thesis) has been generously supported by a Meta Fellowship (cohort of 2020), the Khoury PhD Research Award (2022), and a Northeastern University Dissertation Fellowship (2023). Before joining Northeastern, I received the Electrical and Computer Engineering diploma from the National Technical University of Athens and the MSc on Logic, Algorithms, and Theory of Computation from the University of Athens. During my studies in Greece, I was advised by Dimitris Fotakis.

[August 2025] I hold weekly office hours as part of a broader Learning Theory Alliance initiative. You're welcome to book a time to chat with me here.
[June 2025] If you're going to COLT, make sure to join our LeT-All community event featuring a fireside chat with Peter Bartlett and Vitaly Feldman, group activities, and mentorship roundtables!
[June 2025] I'll give a keynote talk on directions in DP statistics I find exciting at Theory and Practice of Differential Privacy 2025.

Dimension-free Private Mean Estimation for Anisotropic Distributions [arxiv]

Yuval Dagan, Xuelin Yang, Michael I. Jordan, Lydia Zakynthinou, Nikita Zhivotovskiy.
38th Conference on Neural Information Processing Systems (NeurIPS'24).
From Robustness to Privacy and Back [arxiv]

Hilal Asi, Jonathan Ullman, and Lydia Zakynthinou.
40th International Conference on Machine Learning (ICML'23).
Covariance-Aware Private Mean Estimation Without Private Covariance Estimation. [arxiv]

Gavin Brown, Marco Gaboardi, Adam Smith, Jonathan Ullman, and Lydia Zakynthinou.
35th Conference on Neural Information Processing Systems (NeurIPS'21).
Selected as a Spotlight presentation
Private Identity Testing for High-Dimensional Distributions. [arxiv]

Clément L. Canonne, Gautam Kamath, Audra McMillan, Jonathan Ullman, and Lydia Zakynthinou.
34th Conference on Neural Information Processing Systems (NeurIPS'20).
Selected as a Spotlight presentation
Reasoning About Generalization via Conditional Mutual Information. [arxiv]

Thomas Steinke and Lydia Zakynthinou.
33rd Annual Conference on Learning Theory (COLT'20).

I gave a tutorial on differential privacy at the Australasian Summer School on Recent Trends in Algorithms. I also taught an advanced session in the Berkeley Math Circle on Differential Privacy. Highly recommend if you're in the Bay area!

Workshop Committee member at Learning Theory Alliance.
Program/reviewing committee member for IEEE S&P, ICML, NeurIPS (Technical and Ethics Reviewer), TPDP, AAAI, FAccT, COLT.