Anna M. Maddux

06511 New Haven, USA

I recently graduated from a PhD program at EPFL Lausanne, where I conducted research under the supervision of Maryam Kamgarpour in the Systems Control and Multiagent Optimization Research (Sycamore) Lab. My research interests lie in the fields of game theory, mechanism design and learning in multi-agent systmes. During my PhD, I developed game-theoretic and learning-based methods for multi-agent systems with constraints and welfare objectives. Motivated by applications in transportation systems, electricity markets, ride-hailing platforms, and multi-robot systems, my research focused on equilibrium analysis and decentralized learning for constrained decision-making, as well as on mechanism design and learning dynamics to improve social welfare.

Prior to my PhD, I obtained a MSc. in Statistics from ETH Zürich (2021), where I did my master’s thesis at the Automatic Control Laboratory (Ifa) under the supervision of Florian Dörfler and Fadoua Balabdaoui. I, furthermore, obtained a BSc. in Mathematics (2019) and a BSc. in Economics (2018) from the Albert-Ludwigs-University Freiburg. In the past, I interned at Daimler Benz and the German federal parliament. Throughout my undergraduate and graduate studies I have been a fellow of the Friedrich Nauman Foundation. I was also a fellow of the Accenture female talent program.

Links: Email Google Scholar ORCID GitHub LinkedIn

Misc: My Erdos number is 5.

Announcements

Aug, 2026	I just wrapped up three months at the Bank for International Settlements (BIS), working on chokepoint shocks to global supply chains.
May, 2026	I am excited to share that I have successfully defended my PhD thesis at EPFL on May 22nd, titled Game-Theoretic Decision Making in Multi-Agent Systems under Constraints and Welfare Objectives.
Jan, 2026	Our joint work Finite-Time Convergence to an $\epsilon$-Efficient Nash Equilibrium in Potential Games with Reda Ouhama and Maryam Kamgarpour was published in Transactions on Control of Network Systems (TCNS).
Dec, 2025	At CDC in Rio de Janeiro, Marko and I presented our recent work on No-Regret Learning in Stackelberg Games with an Application to Electric Ride-Hailing.
Apr, 2025	I am excited to visit Gabriele Farina at MIT for 2 months.

Selected Publications

Game-Theoretic Decision Making in Multi-Agent Systems under Constraints and Welfare Objectives

Anna Maddux

EPFL , 2026

Bib HTML

@phdthesis{maddux2026,
  title = {Game-Theoretic Decision Making in Multi-Agent Systems under Constraints and Welfare Objectives},
  author = {Maddux, Anna},
  year = {2026},
  school = {EPFL},
  doi = {10.5075/epfl-thesis-11663},
  url = {https://infoscience.epfl.ch/entities/publication/c7fada0a-1c12-4f44-bffe-e107ecac2db6},
}

AISTATS

Multi-Agent Learning in Contextual Games under Unknown Constraints

Anna M Maddux , and Maryam Kamgarpour

International Conference on Artificial Intelligence and Statistics (AISTATS), 2024

arXiv Bib HTML

@article{maddux2023multi,
  title = {Multi-Agent Learning in Contextual Games under Unknown Constraints},
  author = {Maddux, Anna M and Kamgarpour, Maryam},
  journal = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
  year = {2024},
}

CDC

No-Regret Learning in Stackelberg Games with an Application to Electric Ride-Hailing

Anna Maddux , Marko Maljkovic , Nikolas Geroliminis , and Maryam Kamgarpour

arXiv preprint arXiv:2504.03745, 2025

Bib

@article{maddux2025no,
  title = {No-Regret Learning in Stackelberg Games with an Application to Electric Ride-Hailing},
  author = {Maddux, Anna and Maljkovic, Marko and Geroliminis, Nikolas and Kamgarpour, Maryam},
  journal = {arXiv preprint arXiv:2504.03745},
  year = {2025},
}

TCNS

Finite-Time Convergence to an ε-Efficient Nash Equilibrium in Potential Games

Anna Maddux , Reda Ouhamma , Hana Catic , and Maryam Kamgarpour

IEEE Transactions on Control of Network Systems, 2026

Bib

@article{maddux2026finite,
  author = {Maddux, Anna and Ouhamma, Reda and Catic, Hana and Kamgarpour, Maryam},
  journal = {IEEE Transactions on Control of Network Systems},
  title = {Finite-Time Convergence to an $\epsilon$-Efficient Nash Equilibrium in Potential Games},
  year = {2026},
  volume = {13},
  number = {2},
  pages = {1083-1095},
  keywords = {Games;Convergence;Nash equilibrium;Heuristic algorithms;Routing;Polynomials;Network systems;Control systems;Artificial intelligence;Approximation algorithms;Game theory;log-linear learning;potential games},
  doi = {10.1109/TCNS.2026.3673502},
}