Collection 2022 - T3 - WS3 - Measure-theoretic Approaches and Optimal Transportation in Statistics
The Wasserstein distance in Optimal transportation has proved to be useful for a wide range of learning tasks such as generative models, domain adaptation or supervised embeddings. It is also an important metric for Topological Data Analysis and Geometric inference. More generally, distances on the space of probability measures, such as the maximum mean discrepancy, have shown to be powerful tools in statistical learning.
Apparaît dans la collection : 2022 - T3 - Geometry and statistics in data sciences
Organisateur(s) Aamari, Eddie ; Aaron, Catherine ; Chazal, Frédéric ; Fisher, Aurélie ; Hoffmann, Marc ; Le Brigant, Alice ; Levrard, Clément ; Michel, Bertrand
Date(s) 21/11/2022 - 25/11/2022
URL associée https://indico.math.cnrs.fr/event/7547/