Quentin BERTRAND - Home

I am a 3rd year PhD student in machine learning at Inria Paris-Saclay (in the Parietal Team), under the supervision of Joseph Salmon and Alexandre Gramfort. I work on the optimization and statistical aspects of high dimensional sparse linear regression applied to brain signals reconstruction. I have a keen interest in coordinate descent algorithms, hyperparameter selection, and the Python programming language. I also develop a python package for fast automatic hyperparameter selection of sparse linear models. Here is a short resume and my list of publications. We are currently looking for interns to work on bilevel optimization for hyperparameter setting starting Spring 2021! Feel free to contact us.

Contact

News

• January 23: our paper Anderson acceleration of coordinate descent was accepted to AISTATS 2021!

• May 3rd, I will give a talk on bilevel optimization for hyperparameter optimization at Institut Montpellierain Alexandre Grothendieck

Past events

• January 4-9: I gave a tutorial on optimization for machine learning at the Data Science Summer School of École polytechnique

• December 10: I presented our paper on Support recovery and sup-norm convergence rates for sparse pivotal estimation at the online statistical learning seminar organized by Malgorzata Bogdan

• November 23: see our new preprint on Anderson acceleration of coordinate descent!

• October 26: I presented our paper on Implicit differentiation of Lasso-type models for hyperparameter optimization in the team of Lorenzo Rosasco

• October 23: see our new preprint on Model identification and local linear convergence of coordinate descent!

• September 9: I presented our paper on Implicit differentiation of Lasso-type models for hyperparameter optimization at SMAI MODE (virtually)

• September 2: I presented our paper on Implicit differentiation of Lasso-type models for hyperparameter optimization in the team of Julie Josse at https://www.ehess.fr

• August 26-28: I presented our paper on Support recovery and sup-norm convergence rates for sparse pivotal estimation at AISTATS 2020 (virtually)

• July 12-19: I presented our work on Implicit differentiation of Lasso-type models for hyperparameter optimization at ICML 2020 (virtually)

• June 28 - July 10, 2020: I attended the Machine Learning Summer School (MLSS) (virtually)

• January 6, 2020: our paper Support recovery and sup-norm convergence rates for sparse pivotal estimation was accepted to AISTATS 2020 in Palermo, Italy

• December 8-15, 2019: I presented our paper Handling correlated and repeated measurements with the smoothed multivariate square-root Lasso at NeurIPS 2019 in Vancouver, Canada

• December 3-4, 2019: I gave a 20min talk on our paper Support recovery and sup-norm convergence rates for sparse pivotal estimation at PGMO days in Palaiseau, France

• October 21-25, 2019: I was awarded a grant from GDR IA to visit Samuel Vaiter in Dijon, France

• October 16-18, 2019: I participated, and gave a 20min oral presentation at Journées du GDR MOA 2019 in Rennes, France