Optimization for Machine Learning / Optimisation pour l’apprentissage automatique

Collection Optimization for Machine Learning / Optimisation pour l’apprentissage automatique

New challenging subjects of statistical machine learning have encouraged collaborations between Statistics, Computer Science and Optimization communities. Driven by the need to tackle statistical problems leading to non-smooth or non-convex problems, and potentially to the treatment of massive data, a growing community of researchers at the intersection of optimization and machine learning has emerged.

The purpose of this conference is to bring together this community to disseminate the most recent developments in such a very dynamic, multidisciplinary researcheld. The most inuential worl-wide researchers from the various areas mentioned will be invited to present their most innovative work. In addition, to encourage interdisciplinary exchanges of young researchers, PhD students and post-doctoral fellows will be invited.

The program of the session will focus on three main themes for which the interaction between researchers from such communities is particularly promising: sparsity, matrix factorization and stochastic optimization for statistics. Although some simple problems are well understood (from the statistical as well as from the algorithmic point of view), many others remain singularly unexplored. The actors of this session, together, have in their disposal the means that are necessary to advance on this research path.


Organizer(s) Boyer, Claire ; d'Aspremont, Alexandre ; Gramfort, Alexandre ; Salmon, Joseph ; Villar, Soledad
Date(s) 3/9/20 - 3/13/20
linked URL https://conferences.cirm-math.fr/2133.html
Give feedback