About Me

I am an Assistant Professor in the department of Computer Science, in the Donald Bren School of Information & Computer Science at UC Irvine and the director of the GOALLab. I am affiliated with the Center for Algorithms and Theory of Computation, the Center for Machine Learning and Intelligent Systems (CML) and the Algorithms, Combinatorics and Optimization Center (ACO). I am also affiliated with Archimedes research unit. Prior to UCI, I was an Assistant Professor in Information Systems at SUTD. Before that I was a MIT Postdoctoral Fellow working with Costis Daskalakis. I obtained my PhD in Algorithms, Combinatorics, and Optimization (ACO) at Georgia Tech, advised by Prasad Tetali. At Georgia Tech, I also obtained a MSc in Mathematics. I did my undergrad studies in National Technical University of Athens.

Interests

I am interested in theory of computation and its interface with online learning in games, optimization (convex, non-convex, min-max), dynamical systems, probability and statistics and their applications to multi-agent Reinforcement Learning.

Links

For courses I have taught see here. I am currently teaching CS 161.
My CV, Google Scholar and DBLP profiles.

Selected Publications

Click here for full list

Efficiently Computing Nash Equilibria in Adversarial Team Markov Games. ICLR 2023 (oral)
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games. ICLR 2022
Depth-Width Trade-offs for ReLU Networks via Sharkovsky’s Theorem. ICLR 2020 (spotlight)
Regression from Dependent Observations. STOC 2019
First-order Methods Almost Always Avoid Saddle Points. Math. Programming 2019.
The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization. NeurIPS 2018
Multiplicative Weights Update with Constant step-size in Congestion Games: Convergence, Limit Cycles and Chaos. NeurIPS 2017 (spotlight)

News

  • 3/2024: Talks at 2024 Informs Optimization Society Conference (IOS24)
  • 1/2024: New paper on bandit feedback in congestion games.
  • 1/2024: PC member for FOCS 2024, AC for ICML, NeurIPS 2024.
  • 1/2024: Two papers got accepted in ICLR 2024.
  • 1/2024: Two papers got accepted in AAAI 2024.
  • 11/2023: Talk at Simons Laufer Mathematical Sciences Institute on learning in two player games.
  • 10/2023: Talk at Informs on Markov polymatrix Games.
  • 10/2023: AC for ICLR 2024, AISTATS 2024.
  • 9/2023: Four papers got accepted in NeurIPS 2023.
  • 6/2023: I'm co-organizing the EC 2023 Mentoring Workshop with Simina Branzei.
  • 5/2023 One paper accepted in EC 2023.
  • 4/2023 One paper accepted in ICML 2023 as oral.
  • 3/2023: Talk on computing Nash equilibria in Markov Games.
  • 2/2023: New paper on time-varying games.
  • 1/2023: Two papers accepted in ICLR 2023, one oral.

Talks

Learning in Bimatrix Games (MSRI talk)
Nash equilibria in Markov Games
Policy Gradient for Markov Potential Games
On first-order methods (UCI ML seminar)
Depth-width tradeoffs for NNs (MiFODS - MIT)

Current Students

Nikolas Patris (2022 - Present, coadvised with Vijay V. Vazirani)
Stelios Stavroulakis (2022 - Present)
Jingming Yan (2023 - Present)

Past Students (chronological order)

Sai Ganesh Nagarajan (PhD ‘21 $\to$ Postdoc at EPFL)
Will Overman (MSc ‘22 $\to$ PhD at Stanford)
Fivos Kalogiannis (MSc ‘24 $\to$ PhD at UCSD)

Past Postdocs

Xiao Wang (Assistant Professor at SUFE)

Committees and Organizing Workshops

Area Chair at Conference on Neural Information Processing Systems (NeurIPS) 2024
Area Chair at International Conference on Machine Learning (ICML) 2024
Annual Symposium on Foundations of Computer Science (FOCS) 2024
Area Chair at International Conference on Learning Representations (ICLR) 2024
Area Chair at International Conference on Artificial Intelligence and Statistics (AISTATS) 2024
EC Mentoring Workshop 2023 and 2024
Conference on Economics and Computation (EC) 2019, 2020, 2021, 2022, 2023
Conference on Web and Internet Economics (WINE) 2019, 2021, 2023
AAAI Conference on Artificial Intelligence (AAAI) 2020

Miscellaneous

International Mathematical Olympiad
International Olympiad in Informatics