Anas Barakat

Anas Barakat

Postdoctoral Fellow

ETH Zurich

I am currently a postdoctoral fellow at ETH Zurich working with Prof. Niao He within the Optimization & Decision Intelligence Group in the department of computer science. My research interests lie broadly in the span of stochastic optimization, learning in games and reinforcement learning.

I obtained my PhD in Applied Mathematics and Computer Science from Institut Polytechnique de Paris at Télécom Paris under the supervision of Prof. Pascal Bianchi and Prof. Walid Hachem. I received my engineering Master’s degree in Applied Mathematics and Computer Science from Télécom Paris and a Master’s degree in Data Science from Université Paris Saclay.

You can find more information about me on my CV.


  • Stochastic optimization
  • Learning in games
  • Reinforcement learning


  • PhD in Applied Mathematics and CS, 2021

    Institut Polytechnique de Paris (Télécom Paris)

  • MSc in Data Science, 2018

    Université Paris Saclay

  • MSc in Applied Mathematics and CS, 2018

    Télécom Paris


(2024). Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players. *Equal contribution. Submitted.

(2024). Policy Mirror Descent with Lookahead. Under review.


(2023). Independent Learning in Constrained Markov Potential Games. AISTATS 2024.


(2023). Reinforcement Learning with General Utilities: Scaling to Large State Action Spaces via Occupancy Measure Approximation. Under review.

(2023). Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity. IEEE CDC 2023.

Proceedings Arxiv

(2021). Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance. Electronic Journal of Statistics 15 (2), 3892-3947.

DOI Arxiv Journal


Invited talk - 4th Symposium on Machine Learning and Dynamical Systems
Invited talk - ICCOPT 2022
Invited talk - 14th CMStatistics International Conference
Invited talk - Seminar of the 'Image, Optimization and Probabilities' (IOP) team
Talk - 2nd Symposium on Machine Learning and Dynamical Systems 2020


  • Journals: Journal of Machine Learning Research (JMLR), Mathematical Programming, SIAM Journal on Optimization (SIOPT), Journal of Optimization Theory and Applications (JOTA), Systems & Control Letters, Mathematics of Control, Signals, and Systems (MCSS).

  • Conferences: NeurIPS, ICML, COLT, AISTATS, IEEE CDC.


ETH Zurich (2022-2024):

Télécom Paris (2018-2021): Teaching Assistant