Anas Barakat

Anas Barakat

Research Fellow

Singapore University of Technology and Design

I am currently a research fellow at Singapore University of Technology and Design working with Georgios Piliouras and Antonios Varvitsiotis.

My research interests lie in the span of optimization, multi-agent learning and reinforcement learning. I am broadly interested in understanding and designing optimization and multi-agent learning dynamics and algorithms for decision making. Motivated by machine learning and (multi-agent) RL applications, I investigate the convergence behavior and analyze the performance of such algorithms when they converge using tools from stochastic approximation, stochastic optimization, game theory and dynamical systems.

Previously, I was a postdoctoral fellow at ETH Zurich working with Niao He in the department of computer science. I obtained my PhD in applied mathematics and computer science from Institut Polytechnique de Paris at Télécom Paris under the supervision of Pascal Bianchi and 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.

News

  • Oct. 2024: Happy to join SUTD as a research fellow to work with Georgios Piliouras and Antonios Varvitsiotis!
  • Sep. 2024: Our paper with Kimon Protopapas `Policy Mirror Descent with Lookahead' got accepted to NeurIPS 2024.

Interests

  • Optimization
  • Learning in games
  • Reinforcement learning
  • Stochastic approximation

Education

  • 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

Research

Olivier Lepel, Anas Barakat (2024). Beyond Expected Returns: A Policy Gradient Algorithm for Cumulative Prospect Theoretic Reinforcement Learning. Under review.

Arxiv

Anas Barakat, Souradip Chakraborty, Peihong Yu, Pratap Tokekar, Amrit Singh Bedi (2024). On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning. Under review.

Arxiv

Pragnya Alatur, Anas Barakat*, Niao He (2024). Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players. IEEE CDC 2024. *corresponding author.

Arxiv

Kimon Protopapas, Anas Barakat (2024). Policy Mirror Descent with Lookahead. To appear in NeurIPS 2024.

Arxiv

Philip Jordan, Anas Barakat, Niao He (2023). Independent Learning in Constrained Markov Potential Games. AISTATS 2024.

Poster Proceedings Arxiv

Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He (2023). Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity. IEEE CDC 2023.

Proceedings Arxiv

Anas Barakat, Ilyas Fatkhullin, Niao He (2023). Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space. ICML 2023.

Poster Slides Proceedings Arxiv

Ilyas Fatkhullin, Anas Barakat, Anastasia Kireeva, Niao He (2023). Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies. ICML 2023.

Poster Proceedings Arxiv

Anas Barakat, Pascal Bianchi, Julien Lehmann (2022). Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation. AISTATS 2022.

Poster Proceedings Arxiv

Anas Barakat (2021). Contributions to non-convex stochastic optimization and reinforcement learning. PhD dissertation.

Slides Thesis

Anas Barakat, Pascal Bianchi, Walid Hachem, Sholom Schechtman (2021). Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance. Electronic Journal of Statistics 15 (2), 3892-3947.

DOI Arxiv Journal

Anas Barakat, Pascal Bianchi (2020). Convergence and Dynamical Behavior of the ADAM Algorithm for Non-Convex Stochastic Optimization. SIAM Journal on Optimization, 31 (1), 244-274.

Poster Slides Video DOI Arxiv Journal

Anas Barakat, Pascal Bianchi (2019). Convergence Rates of a Momentum Algorithm with Bounded Adaptive Step Size for Non-Convex Optimization. ACML 2020.

Poster Slides Proceedings Arxiv

Anas Barakat, Pascal Bianchi (2019). Convergence de l'algorithme Adam du point de vue des systèmes dynamiques. GRETSI 2019.

PDF Slides

Talks

Invited talk - 4th Symposium on Machine Learning and Dynamical Systems
Jul 8, 2024 2:45 PM Fields Institute, Toronto, Canada
Invited talk - ICCOPT 2022
Jul 28, 2022 3:00 PM Lehigh University, Bethlehem, USA
Invited talk - 14th CMStatistics International Conference
Dec 20, 2021 2:45 PM King’s College, London, United Kingdom (hybrid)
Invited talk - Seminar of the 'Image, Optimization and Probabilities' (IOP) team
Oct 15, 2020 11:00 AM Institut de Mathématiques de Bordeaux
Talk - 2nd Symposium on Machine Learning and Dynamical Systems 2020
Sep 21, 2020 5:40 PM Fields Institute for Research in Mathematical Sciences, Toronto, online
See all talks

Reviewing

  • 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), Stochastic Systems, IEEE Transactions on Automatic Control, IEEE Control Systems Letters, Transactions on Machine Learning Research (TMLR).

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

Teaching

ETH Zurich (2022-2024):

Télécom Paris (2018-2021): Teaching Assistant

Contact