Welcome! I am a PhD student in the theory group of the Khoury College of Computer Sciences at Northeastern University, where I am very fortunate to be advised by Huy Lê Nguyễn and Jonathan Ullman. My research interests lie in the theoretical foundations of machine learning and data privacy.
I am in my final year and looking for postdoc positions!
I spent the Summer of 2022 as an intern at Apple Research, where I worked on the shuffle model of differential privacy with my mentor Audra McMillan. Audra and the Privacy team at Apple are great hosts!
During Summer 2019 and 2020, I interned at IBM Research - Almaden, where I was lucky to be mentored by Thomas Steinke and work with him on the generalization properties of machine learning algorithms.
For the past two academic years, between Fall 2020-Spring 2022, my research had been generously supported by a Facebook Fellowship.
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 [last update: October 2022].
[October 2022] New paper on arXiv! Multitask Learning via Shared Features: Algorithms and Hardness with Konstantina Bairaktari, Guy Blanc, Li-Yang Tan, and Jonathan Ullman. We wrote this paper while visiting Stanford last Spring and are grateful for the hospitality of Li-Yang, our host Omer Reingold, and their students.
[July 2022] My plenary talk at TPDP can be found here.
[May 2022] I received the PhD Research Award from Khoury College! Thank you so much to everyone at Khoury who helped create a supportive environment.
Covariance-Aware Private Mean Estimation Without Private Covariance Estimation. [arxiv]
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes. [arxiv]
Differentially Private Decomposable Submodular Maximization. [arxiv]
Private Identity Testing for High-Dimensional Distributions. [arxiv]
Reasoning About Generalization via Conditional Mutual Information. [arxiv]
Thomas Steinke and Lydia Zakynthinou.
33rd Annual Conference on Learning Theory (COLT'20).
Efficient Private Algorithms for Learning Large-Margin Halfspaces. [arxiv]
Improved Algorithms for Collaborative PAC Learning. [arxiv]
Huy Lê Nguyễn and Lydia Zakynthinou.
32nd Conference on Neural Information Processing Systems (NeurIPS’18), Montréal, Canada, 2018.
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).
- Program/reviewing committee member for ICML 2020-2022, NeurIPS 2020-2022 (Technical and Ethics Reviewer for 2022), TPDP 2020-2021, AAAI 2020, FAccT 2020-2022.
- 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 - now).
- Student representative of the Khoury College's Faculty Hiring Committee for the hiring season of 2020-2021.