I am a PhD student in the Department of Mathematics at the National and Kapodistrian University of Athens and an Academic Fellow at the Archimedes Research Unit, Athena Research Center, advised by Panayotis Mertikopoulos and Ioannis Panageas.
I have also been a visiting doctoral fellow at the LIONS group at EPFL, hosted by Volkan Cevher, and at UC Irvine with Ioannis Panageas. Before that, I worked as a research assistant at the Max Planck Institute for Software Systems, supervised by Goran Radanovic.
I hold a M.Eng. in Electrical and Computer Engineering from the National Technical University of Athens. For more information, see my Google Scholar, DBLP, or CV.
My research develops and analyzes learning algorithms for games and optimization problems where classical convexity assumptions no longer apply. I am especially interested in equilibrium computation, learning dynamics in non-convex games, bandit and zeroth-order feedback, and efficient methods for problems with large combinatorial action spaces. A complementary thread of my work studies the computational complexity of stationarity and equilibrium notions, aiming to understand not only which algorithms converge, but also where algorithmic barriers are intrinsic.
News
May 2026 - Our paper, The Complexity of Computing Coarse Correlated Equilibria in Markov Games with a Single Controller, is now available on arXiv.
May 2026 - Our paper, Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback, is now available on arXiv.
May 2026 - Our paper, Efficient Swap Regret Minimization in Combinatorial Bandits, was accepted at AISTATS 2026.
April 2026 - Our paper, The Computational Complexity of Avoiding Strict Saddle Points in Constrained Optimization, is now available on arXiv.
December 2025 - Our paper, Efficient Kernelized Learning in Polyhedral Games Beyond Full-Information: From Colonel Blotto to Congestion Games, was accepted at NeurIPS 2025.
February 2025 - Our paper, On Corruption-Robustness in Performative Reinforcement Learning, was accepted at AAAI 2025 (accepted as an oral presentation).
July 2024 - Our paper, The Computational Complexity of Finding Second-Order Stationary Points, appeared at ICML 2024.