Guillaume Garrigos
My research essentially focuses on dynamical systems associated to optimization problems. In particular, I am interested in algorithms and regularization methods for nonsmooth (eventually nonconvex) problems arising in signal/image processing, inverse problems, and machine learning. I also have some taste for multi-objective optimization problems.
I have postdoctoral position at the Laboratory for Computational and Statistical Learning, fruit of the collaboration between the Istituto Italiano di Tecnologia and the Massachusetts Institute of Technology. I'm here in charge of the Machine Learning Tutorials.
News
-
Aug12017
Paper accepted
Our paper "Iterative regularization via dual diagonal descent" has been accepted in Journal of Mathematical Imaging and Vision. It is available on the editor website and arXiv. See also some recent slides.
-
Jul5-72017
Journées Franco-Chiliennes d'Optimisation 2017
I got the pleasure of being invited to give a talk at the am part of the organization and teaching board of JFCO 2017, a conference celebrating the collaboration between the French and Chilean schools in optimization.
Title: "Optimization in inverse problems via Iterative regularization" (slides)
-
May2-62017
RegML 2017
I am part of the organization and teaching board of RegML 2017, a spring school on Regularization Methods for Machine Learning. This year, the event is held at Simula, in Oslo.
-
Feb142017
Seminar at INRIA Paris (SIERRA)
I am visiting the SIERRA team at INRIA Rocquencourt, and I will give a talk about the geometry of convex functions and their influence on the complexity of algorithms.
-
Feb092017
Seminar in Institut de Mathématiques de Toulouse
I am invited by Edouard Pauwels to give a talk in the workgroup Mathématiques de l'apprentissage.
-
Dec122016
Stay in Chile
I'm visiting Juan Peypouquet at Santiago for two weeks. I will give two talks, one at the CMM on Dec 14, one at the USM on Dec 19.
-
Dec52016
NIPS 2016
I am attending the NIPS conference which is held in Barcelona. I will present a poster at the Optimization workshop, on Dec 10, about our recent work Iterative regularization via dual diagonal descent.
-
Oct72016
Preprint
We submitted with Lorenzo Rosasco and Silvia Villa a paper called Iterative regularization via dual diagonal descent, whose preprint is available on arXiv.
-
Aug92016
Conference
I attended the ICCOPT conference in Tokyo (Japan). I gave there a talk about how the geometry of a function determine the convergence rates of descent methods (find the slides here). It is based on a previous paper and a forthcoming one.
-
Mar232016
Conference
I gave a talk at the Journées Annuelles du groupe MODE, which were organized this year in Toulouse (France). See my slides here.
-
Dec022015
Conference
I gave a talk at the Journées Annuelles du GdR MOA, which were organized this year in Dijon (France). See my slides here.
-
Nov022015
Ph.D.
After a successful defence, I obtained a PhD in Applied Mathematics, delivered by the Université de Montpellier (France) and the Universidad Tecnica Federico Santa Maria (Chile). This concludes three great years of working with Hédy Attouch and Juan Peypouquet. My dissertation can be found here (with some slides).
-
Oct012015
Post-doc position
I am starting a post-doc at the Laboratory for Computational and Statistical Learning (Genova, Italy), to work with Lorenzo Rosasco and Silvia Villa on optimization for machine learning.
-
Jul142015
Conference
I gave a talk at the 22nd International Symposium on Mathematical Programming (Pittsburgh, USA).