Next seminars:
April 4th, 2024, 14h, room Amphitheater of the IMAG building.
Jérôme Malick (CNRS, LJK (Grenoble))
Title: Towards more resilient, robust, responsible decisions
Abstract: Machine/deep learning work incredibly well... until it doesn't. In this presentation, I will present an approach producing resilient solutions (distributionnally robust optimization with Wasserstein uncertainty). I will emphasize the ideas, provide illustrations, and highlight the collaborative work on this topic at DAO. In particular, I will mention (1) the statistical properties of robust models, (2) a nice histogram reshaping, (3) a toolbox (with scikit-learn and PyTorch interfaces) to robustify your own models !
May 2nd, 2024, 14h, room TBA.
Freddy Bouchet (CNRS, ENS Lyon)
Title: TBA
Abstract: TBA
June 6th, 2024, 14h, room TBA.
Alain Durmus (Ecole Polytechnique)
Title: TBA
Abstract: TBA