The design of machines capable of intelligent comprehension and decision-making is one of the major scientific and technological challenges of our time, requiring new models, new algorithms, and new analytical paradigms.
In this chair, we intend to draw on optimization and game theory to make concrete advances in the mathematical foundations of AI.
Yu-Guan Hsieh, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos. Optimization in Open Networks via Dual Averaging. CDC 2021—60th IEEE Annual Conference on Decision and Control, Dec. 2021, Austin, United States. pp. 1–7
Waïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos. “The Last-Iterate Convergence Rate of Optimistic Mirror Descent in Stochastic Variational Inequalities.” COLT 2021—34th Annual Conference on Learning Theory, Aug. 2021, Boulder, United States. pp. 1–32.
Franck Iutzeler, Mathias Chastan, Auguste Lam. Unsupervised density-based machine learning for the detection of abnormal leveling signatures.SPIE Advanced Lithography, Feb. 2021, Online Only, United States. p. 51.
Franck Iutzeler, Jérôme Malick. “Nonsmoothness in Machine Learning: Specific Structure, Proximal Identification, and Applications.” *Set-Valued and Variational Analysis*, Springer, 2020, 28 (4), pp. 661–678.
Published on October 14, 2026 Updated on October 14, 2026
Geometry of optimization problems arising in learning
Guarantees for robust/adversarial learning
Distributed/online optimization algorithms
Risk-sensitive learning and optimization
Share the linkCopyCopiedClose the modal windowShare the URL of this pageI recommend this page:Available at this address:The page will then be accessible from your "My Favorites" menu.Stop the videoPlay the videoMutePlay audioChat: Have a question?Robo Fabrica ChatbotMatomo Traffic StatisticsX (formerly Twitter)
