Lydia Zakynthinou
PhD Student
Education
- MS, University of Athens - Greece
- BS in Electrical and Computer Engineering, National Technical University of Athens - Greece
Biography
Lydia Zakynthinou is a PhD student in the Computer Science program at Northeastern University’s Khoury College of Computer Sciences, advised by Professors Jonathan Ullman and Huy Lê Nguyễn. Before joining Northeastern, Lydia earned a diploma in Electrical and Computer Engineering from the National Technical University of Athens and a Master of Science from the University of Athens. Her research interests lie in the areas of learning theory and differential privacy.
What are the specifics of your graduate education (thus far)?
I have completed the graduate program on Algorithms, Complexity and Theory of Computation in Athens and I am now in my fifth year in the PhD program.
What are your research interests?
My research interests lie in the theoretical foundations of machine learning and data privacy. My work focuses on designing learning algorithms for fundamental statistical problems that provably preserve the privacy of the individuals' data as well as on understanding the properties that learning algorithms need to satisfy so that their empirical performance is a good indication of their performance in the real world.
Where did you grow up or spend your most defining years?
I grew up in Athens, Greece.
Where did you study for your undergraduate degree?
I studied in the School of Electrical and Computer Engineering of the National Technical University of Athens. This is a five year program encompassing a wide range of the ECE knowledge and consisting of two periods; the first building a diverse background (core) and the second specializing in a preferred concentration field (MEng).
Recent Publications
-
Improved Algorithms for Collaborative PAC Learning
Citation: Huy Lê Nguyễn and Lydia Zakynthinou. "Improved Algorithms for Collaborative PAC Learning." Advances in Neural Information Processing Systems 31 (NeurIPS’18), 2018. -
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
Citation: Peter Grünwald, Thomas Steinke and Lydia Zakynthinou. PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes. In Proceedings of the 34th Annual Conference on Learning Theory (COLT), 2021. -
Differentially Private Decomposable Submodular Maximization
Citation: Anamay Chaturvedi, Huy Lê Nguyễn, and Lydia Zakynthinou. Differentially Private Decomposable Submodular Maximization. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), 2021.
