Hi! I am an FDS Postdoctoral Fellow at Yale University. Before that, I was a PhD student in the Computer Science Department of the National Technical University of Athens (NTUA) working with Dimitris Fotakis and Christos Tzamos. I completed my undergraduate studies in the School of Electrical and Computer Engineering Department of the NTUA, where I was advised by Dimitris Fotakis.

Research: My research focuses on Machine Learning Theory and its interplay with Statistics & High-Dimensional Probability, Optimization and Computational Complexity. Currently, I am interested in questions regarding the following topics:

1. Robustness and Stability in Learning: Inference from Biased Data, Private/Replicable/Fair Algorithm Design
2. Statistical Learning Theory: PAC Learning, Universal Learning, Distribution Learning, Expressiveness
3. Complexity of Optimization: Nonconvex Optimization, Equilibrium Computation, Gradient Descent Dynamics

Contact me at: alvertos.kalavasis [at] yale.edu

My amazing collaborators (in roughly chronological order): Dimitris Fotakis, Christos Tzamos, Konstantinos Stavropoulos, Vasilis Kontonis, Manolis Zampetakis, Jason Milionis, Stratis Ioannidis, Eleni Psaroudaki, Grigoris Velegkas, Amin Karbasi, Hossein Esfandiari, Andreas Krause, Vahab Mirrokni, Constantine Caramanis, Shay Moran, Idan Attias, Steve Hanneke, Andreas Galanis, Anthimos Vardis Kandiros, Ioannis Anagnostides, Tuomas Sandholm.

Publications

1. On the Complexity of Computing Sparse Equilibria and Lower Bounds for No-Regret Learning in Games
   with Ioannis Anagnostides, Tuomas Sandholm and Manolis Zampetakis
   ITCS 2024
2. Learning Hard-Constrained Models with One Sample
   with Andreas Galanis and Anthimos Vardis Kandiros
   SODA 2024
3. Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods
   with Constantine Caramanis, Dimitris Fotakis, Vasilis Kontonis and Christos Tzamos
   NeurIPS 2023 Selected as Oral
   [Code]
4. Optimal Learners for Realizable Regression: PAC Learning and Online Learning
   with Idan Attias, Steve Hanneke, Amin Karbasi and Grigoris Velegkas
   NeurIPS 2023 Selected as Oral
5. Statistical Indistinguishability of Learning Algorithms
   with Amin Karbasi, Shay Moran and Grigoris Velegkas
   ICML 2023
6. Replicable Bandits
   with Hossein Esfandiari, Amin Karbasi, Andreas Krause, Vahab Mirrokni and Grigoris Velegkas
   ICLR 2023
7. Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes
   with Grigoris Velegkas and Amin Karbasi
   NeurIPS 2022
8. Learning and Covering Sums of Independent Random Variables with Unbounded Support
   with Konstantinos Stavropoulos and Manolis Zampetakis
   NeurIPS 2022 Selected as Oral
9. Perfect Sampling from Pairwise Comparisons
   with Dimitris Fotakis and Christos Tzamos
   NeurIPS 2022
10. Linear Label Ranking with Bounded Noise
    with Dimitris Fotakis, Vasilis Kontonis and Christos Tzamos
    NeurIPS 2022 Selected as Oral
11. Label Ranking through Nonparametric Regression
    with Dimitris Fotakis and Eleni Psaroudaki
    ICML 2022 Selected for Long Presentation
12. Differentially Private Regression with Unbounded Covariates
    with Jason Milionis, Dimitris Fotakis and Stratis Ioannidis
    AISTATS 2022
13. Efficient Algorithms for Learning from Coarse Labels
    with Dimitris Fotakis, Vasilis Kontonis and Christos Tzamos
    COLT 2021
14. Aggregating Incomplete and Noisy Rankings
    with Dimitris Fotakis and Konstantinos Stavropoulos
    AISTATS 2021
15. Efficient Parameter Estimation of Truncated Boolean Product Distributions
    with Dimitris Fotakis and Christos Tzamos
    COLT 2020

1. Efficient Parameter Estimation of Truncated Boolean Product Distributions
   with Dimitris Fotakis and Christos Tzamos
   Algorithmica