The design of machines capable of intelligent comprehension and decision making is one of the major current scientific and technological challenges, calling for new models, new algorithms, and new analysis paradigms.
In this chair, we intend to leverage on optimization and game theory to make concrete advances on 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 abnormal leveling signatures detection. SPIE Advanced Lithography, Feb 2021, Online Only, United States. pp.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.
Publié le 14 octobre 2026 Mis à jour le 14 octobre 2026
Geometry of optimization problems arising in learning
Guarantees for robust/adversial learning
Distributed/online optimization algorithms
Risk-sensitive learning and optimization
Partager le lienCopierCopiéFermer la fenêtre modalePartager l'URL de cette pageJe recommande cette page :Consultable à cette adresse :La page sera alors accessible depuis votre menu "Mes favoris".Arrêter la vidéoJouer la vidéoCouper le sonJouer le sonChat : Une question ?Chatbot Robo FabricaStatistiques de fréquentation MatomoX (anciennement Twitter)