Scholar
Argyris Mouzakis
Google Scholar ID: mFbLNZQAAAAJ
PhD Student, University of Waterloo
Citations & Impact
Citations
151
H-index
4
i10-index
3
Publications
6
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Optimal Differentially Private Sampling of Unbounded Gaussians
- - Private Mean Estimation with Person-Level Differential Privacy
- - Not All Learnable Distribution Classes are Privately Learnable
- - A Bias-Variance-Privacy Trilemma for Statistical Estimation
- - New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma
- - A Private and Computationally Efficient Estimator for Unbounded Gaussians
Research Experience
- PhD student at the Cheriton School of Computer Science, University of Waterloo; Member of The Salon
Education
- PhD: Cheriton School of Computer Science, University of Waterloo, advised by Gautam Kamath; BSc: Electrical and Computer Engineering (ECE), National Technical University of Athens (NTUA), advised by Dimitris Fotakis
Background
- Research interests lie at the intersection of Theoretical Computer Science and Statistics, with a particular focus on Machine Learning Theory, Algorithmic Statistics, and Differential Privacy.
Miscellany
- Personal interests: Tutorial link provided for name pronunciation; Pronouns: identifies as a cisgender man but is fine with anything respectful; Recipient of a scholarship from the Onassis Foundation since September 2023 for doctoral studies; Plans to graduate by the end of the 2025-2026 academic year and is looking for postdoc positions starting Fall 2026
