Other titles and affiliations
Yassine Yaakoubi is a postdoctoral researcher in Mine Planning and Optimization under the supevision of Professor Roussos Dimitrakopoulos (COSMO). His research interests lie in combining machine learning and mathematical programming to solve large-scale combinatorial optimization problems. Yassine completed his PhD in December 2019 under Professors François Soumis (Polytechnique Montréal and GERAD) and Simon Lacoste-Julien (University of Montréal and MILA), where he investigated the use of various machine learning methods to warm-start an airline crew scheduling solver based on column generation and constraint aggregation. His current research looks at designing new reactive/learning metaheuristics to optimize smart(er) industrial mining complexes. Beyond imitation learning, where useful knowledge from past solutions is extracted to improve the efficiency and the effectiveness of metaheuristics, Yassine is particularly interested in using reinforcement learning in conjunction with a multi-neighborhood simulated annealing algorithm where the selection of the perturbation is made in self-adaptive learning.
Cahiers du GERAD
Learning to schedule heuristics for the simultaneous stochastic optimization of mining complexes
The simultaneous stochastic optimization of mining complexes (SSOMC) is a large-scale stochastic combinatorial optimization problem that simultaneously manag...BibTeX reference
An improved integral column generation algorithm using machine learning for aircrew pairing
The crew pairing problem (CPP) is solved in the first step of the crew scheduling process. It consists of creating a set of pairings (sequence of flights, co...BibTeX reference