Title: Optimisation des hyperparamètres des réseaux de neurones profonds
Chun Cheng won the 2020 GERAD Best Thesis Competition for her thesis titled "Robust Optimization for Supply Chain Applications: Facility Location and Drone Delivery Problems". She was supervised by Yossiri Adulyasak at HEC Montréal and Louis-Martin Rousseau at Polytechnique Montréal.
Sanae Lotfi, a graduate of the Master of research in applied mathematics, has received the Best Master’s Thesis Award of the Department of Mathematics and Industrial Engineering, Polytechnique Montréal.
Here are the winners who will each receive a half-fellowship of $30,000:
- Dengwang Tang, candidate proposed by Aditya Mahajan;
- Shanshan Wang, candidate proposed by Leandro Coelho and Erick Delage;
- Lingxiao Wu, candidate proposed by Jean-François Cordeau and Yossiri Adulyasak.
This article, published in the prestigious journal Nature, shows that in France, many COVID-19 patients have not consulted or alerted public health to their condition, leading to problematic under-detection of cases. This study is based on a mathematical model, the parameters of which were optimized using the NOMAD software developed at GERAD by the team of professors Charles Audet and Sébastien Le Digabel and the research associates Viviane Rochon Montplaisir and Christophe Tribes. This blackbox optimization software has been in continuous development for over twenty years and represents the state of the art in derivative-free optimization.
The last issue of the Newsletter is now available. Enjoy!
- Spotlights on ... - A project finalist for the ADRIQ Award
- *Collaborations * - GERAD, a partner to the first Edge Intelligence Workshop
- *Actions and interactions * - Best practices when writing a scientific paper in decision science according to Gilbert Laporte
- Who are they? - Yichuan Ding, Mélina Mailhot
- Where are they now? - Masoud Chitsaz, Elias Khalil, Nahid Masoudi
- Postdoctoral fellows - Tarik Bahraoui, Simon Belieres, Julien Fageot, Sriram Sankaranarayanan
GERAD researchers have developed models to identify the most economically efficient GHG reduction scenarios and the optimal time to implement them.