Le lundi 23 novembre 2020 à 13:45 - UM - Bât 09 - Salle de conférence (1er étage)Franck Iutzeler
Nonsmooth regularizations are often used in machine learning in order to promote some structure on the sought model. In this talk, we will investigate how this specific structure appears in terms of minimization of the regularized empirical risk. Then, building upon this, we will illustrate how to leverage this structure in practice for compression, acceleration, or dimension reduction.
WEBINAIRE ouvert à toutes et tous : https://umontpellier-fr.zoom.us/j/85813807839