Welcome to the seminars of the GAIA team (Géométrie, Apprentissage, Information, Algorithmes) of GIPSA-lab. The objective of GAIA seminars is to invite, about every two months, well-known researchers in signal processing and machine learning (and more…) to give an introductive seminar on their research field. Everybody is welcome to join, you can subscribe to the mailing list below.

Next seminar

April 4th, 2024, 14h, 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, TBA.
Freddy Bouchet (CNRS, ENS Lyon)
Title: TBA
Abstract: TBA

June 6th, 2024, 14h, TBA.
Alain Durmus (Ecole Polytechnique)
Title: TBA
Abstract: TBA

Mailing list

To receive informations about the seminars (especially if you want to receive a videoconference link when there is one), subscribe to the mailing list here.

Organizers

• Nicolas Tremblay (CNRS, GIPSA-lab)
• Simon Barthelme (CNRS, GIPSA-lab)

Contact

firstname.name [at] gipsa-lab.grenoble-inp [dot] fr