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 and machine learning. I am particularly interested in the interplay between the modelization of a learning/inverse problem as an optimization problem, and its resolution. I also have some taste for multiobjective optimization problems. My papers are here.
I am a CNRS postdoc researcher at the École Normale Supérieure (DMA), member of the NORIA (Numerical Optimal tRansport for ImAging) research group.
Formerly, I used to be a postdoc researcher at the Laboratory for Computational and Statistical Learning, a joint lab between the IIT and MIT. Before that I did a PhD in Optimization between the Université de Montpellier and the Universidad Santa Maria.
Upcoming news

May 2125 2018: I will give a talk at the "Inverse Problems: Modeling and Simulation" 9th conference, in the minisymposium "Convex Analysis and Inverse Problems", Malta.
Jun 0508 2018: I will give a talk at the SIAM Conference on Imaging Science, in the minisymposium "Optimization for imaging and big data", Bologna.
Sep 0307 2018: I will give a talk at the European Signal Processing Conference (EUSIPCO), in the special session "Representation learning for signal processing", Roma.
News

Feb212018
Seminars : a Winter Tour
In the last three months I have been presenting my work on Iterative regularization for inverse problems in a few places. A poster at the MIA conference (Berlin, Jan 15), and talks at the Séminaire LJKProbabilités & Statistique (Grenoble, Dec 7), VColoquio (Valparaison, Chile, Dec 11), Séminaire CVN (École Centrale Paris, Jan 20), LCSL Machine Learning Seminar (Universita di Genova, Italy, Jan 29), Séminaire Images Optimisation et Probabilités (Université de Bordeaux, Feb 07), Séminaire commun de Statistique P6P7 (Paris, Feb 20). Slides of my talk can be found here.

Dec142017
Workshop
I spoke at the Workshop on Dynamics and Algorithms in Convex Optimization in Santiago de Chile, about optimization and inverse problems.

Nov182017
Workshop
I was at the workshop "Gradient dynamics, convergence and related topics" organized by Jérome Bolte and Sylvain Sorin at Université Pierre et Marie Curie, Paris. I gave a talk intitled "Quadratic functions in Hilbert spaces: Lojasiewicz inequality and Sobolev regularity", based on the work done in this paper (see Section 5.1).

Oct172017
Conference
I was participating to the annual conference of the GdR MOA (Mathématiques de l'Optimisation et Applications), organized this year in Bordeaux, together with the GdR MIA. I gave a talk on the rates of optimization methods and their interplay with inverse problems.

Oct012017
Postdoc position
I am starting a postdoc at the École Normale Supérieure in Paris, where I am part of the new NORIA (Numerical Optimal tRansport for ImAging) research group. I will collaborate with Gabriel Peyré on inverse problems in imaging and optimal transport.

Sep82017
Conference
I was invited to give a talk by Clément Royer, who were organizing a session at Optimization 2017, a conference organized this year in Lisboa.

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.

Jul572017
Conference
I got the pleasure of being invited to give a talk at the Journées FrancoChiliennes d'Optimisation 2017, a conference celebrating the collaboration between the French and Chilean schools in optimization.
Title: "Optimization in inverse problems via Iterative regularization" (slides)

May262017
Organization of spring school in Machine Learning
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
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
I am invited by Edouard Pauwels to give a talk in the workgroup Mathématiques de l'apprentissage, at the Institut de Mathématiques de Toulouse.

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
Conference
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
Postdoc position
I am starting a postdoc 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).