About
I am 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. During my PhD, I interned at Apple, under the mentorship of Audra McMillan, and at IBM Research, under the mentorship of Thomas Steinke. 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.
You can find my full CV here.
News
- [October 2024] I'll be in Sydney Dec 3-6 to give a tutorial on differential privacy at the Australasian Summer School on Recent Trends in Algorithms.
- [October 2024] We are organizing a social at NeurIPS in Vancouver Learning Theory Alliance. Sign up for updates to register and attend!
Selected Publications
-
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).
Teaching
I recently 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!
During Fall '18, I was a teaching assistant for the undergraduate course Algorithms and Data (CS3000), at Northeastern University. I also taught a couple of lectures on Intractability in this year's PhD-level Advanced Algorithms course, taught by Jon.
Between Fall '14 and Spring '17, I had been a teaching assistant for several courses at the National Technical University of Athens: Algorithms and Complexity (undergraduate and graduate), Algorithmic Game Theory (graduate), Social Networks (graduate), Computer Programming (undergraduate), and Introduction to Computer Science (undergraduate).
Service
- Organizer for Learning Theory Alliance's Mentorship Workshop in Fall 2023 and Summer 2024.
- Program/reviewing committee member for ICML, NeurIPS (Technical and Ethics Reviewer), TPDP, AAAI, FAccT, COLT.
- Organizer for the Boston-area Differential Privacy Seminar (Spring 2021), the NEU Theory Seminar (Spring 2019-Fall 2021) and the Khoury PhD Women Group (Spring 2019 - 2023).
- Student representative of the Khoury College's Faculty Hiring Committee for the hiring season of 2020-2021.