Please find my new website at lydiazakynthinou.com.

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 had 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 [updated February 2023].

News

  • [August 2023] I joined the Learning Theory Alliance's Mentorship Workshop Organizing Committee. Look out for a workshop announcement soon!
  • [July 2023] I completed my PhD defense! My thesis can be found here.

  • [July 2022] My plenary talk at TPDP can be found here.

Publications

  • From Robustness to Privacy and Back [arxiv]

    Hilal Asi, Jonathan Ullman, and Lydia Zakynthinou.
    40th International Conference on Machine Learning (ICML'23), Honolulu, USA, 2023.

  • Multitask Learning via Shared Features: Algorithms and Hardness [arxiv]

    Konstantina Bairaktari, Guy Blanc, Li-Yang Tan, Jonathan Ullman, and Lydia Zakynthinou.
    36th Annual Conference on Learning Theory (COLT'23), Bangalore, India, 2023.

  • 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

  • PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes. [arxiv]

    Peter Grünwald, Thomas Steinke and Lydia Zakynthinou.
    34th Annual Conference on Learning Theory (COLT'21), Boulder, USA, 2021.

  • Differentially Private Decomposable Submodular Maximization. [arxiv]

    Anamay Chaturvedi, Huy Lê Nguyễn, and Lydia Zakynthinou.
    35th AAAI Conference on Artificial Intelligence (AAAI'21).

  • 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).

  • Efficient Private Algorithms for Learning Large-Margin Halfspaces. [arxiv]

    Huy Lê Nguyễn, Jonathan Ullman, and Lydia Zakynthinou.
    31st International Conference on Algorithmic Learning Theory (ALT'20), San Diego, USA, 2020.

  • 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.

Teaching

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

Misc.

I like to sing! I very self-conciously put this back up here following Omer Reingold's encouragement, with the hope that I will start spending more time playing music soon.