Dounia Lakhmiri
Student (Postdoctoral), GERAD

Other titles and affiliations
Sep 2010 – Sep 2013
ENSEEIHT
Education
since Jun 2021
Postdoctoral research
Polytechnique Montréal – Department of Mathematics and Industrial Engineering,
Dominique Orban,
director,
Andrea Lodi,
co-director
Jan 2017 – Apr 2021
Ph.D.
Optimisation des hyperparamètres des réseaux de neurones profonds
Polytechnique Montréal – Department of Mathematics and Industrial Engineering,
Sébastien Le Digabel,
director
Sep 2014 – Jun 2016
Master's degree
Implementation of methods for derivative-free optimization
Polytechnique Montréal – Department of Mathematics and Industrial Engineering,
Dominique Orban,
director
Mar 2013 – Sep 2013
Internship
Méthode de gradient conjugué projeté pour minimiser une quadratique convexe sous contraintes de bornes
Polytechnique Montréal,
Dominique Orban,
director
Jul 2012 – Aug 2012
Internship
Résolution itérative de systèmes linéaires provenant de l'optimisation avec contraintes
Polytechnique Montréal,
Dominique Orban,
director
Publications
Mar 2022
Dounia Lakhmiri, Ryan Alimo, and Sébastien Le Digabel
Expert Systems with Applications, 168, Paper no: 116060, 2022
BibTeX reference
Mar 2022
Dounia Lakhmiri and Sébastien Le Digabel
Operations Research Forum, 3(1), Paper no: 11, 2022
BibTeX reference
Jun 2021
Dounia Lakhmiri, Sébastien Le Digabel, and Christophe Tribes
ACM Transactions on Mathematical Software, 47(3), 27 pages, 2021
BibTeX reference
News
Apr 12, 2021
Title: Optimisation des hyperparamètres des réseaux de neurones profonds
Events
May 20, 202211:00 AM — 01:00 PM
DS4DM Coffee Talk
Dounia Lakhmiri – Polytechnique Montréal
Dounia Lakhmiri – Polytechnique Montréal
Canada Excellence Research Chair in Data Science for Real-Time Decision-Making
Hybrid seminar
Nov 10, 202111:00 AM — 12:00 PM
“Meet a GERAD researcher!” seminar
Dounia Lakhmiri – Polytechnique Montréal
Dounia Lakhmiri – Polytechnique Montréal
Online meeting
Cahiers du GERAD
Mar 2021
Dounia Lakhmiri and Sébastien Le Digabel
Optimizing the hyperparameters and architecture of a neural network is a long yet necessary phase in the development of any new application. This consuming p...
BibTeX reference
Jun 2020
The Mars Curiosity rover is frequently sending back engineering and science data that goes through a pipeline of systems before reaching its final destinati...
BibTeX reference
Jul 2019
G-2019-46
HyperNOMAD: Hyperparameter optimization of deep neural networks using mesh adaptive direct search
HyperNOMAD: Hyperparameter optimization of deep neural networks using mesh adaptive direct search
The performance of deep neural networks is highly sensitive to the choice of the hyperparameters that define the structure of the network and the learning pr...
BibTeX referenceSupervision

Mathilde Ricard
Internship