Message > Internship position, ISAE-SUPAERO, Toulouse, France
Le 16/06/2017 par emmanuelr :
An internship position is available in the ML & OR team at ISAE-SUPAERO, in Toulouse, France. See description below.
Candidates should write to email@example.com and firstname.lastname@example.org.
The Department of Complex Systems Engineering at ISAE-SUPAERO is offering an internship
position, for a duration of up to 6 months, starting july (or as early as possible).
The candidate work will fall within the “Learning4Opt” project and will be tutored by E. Rachelson
(ISAE-SUPAERO professor) and L. Mossina (PhD student).
The team is currently working on recurrent combinatorial optimization problems — problems that
require the resolution of similar instances over time. Often, this process is time-constrained, leading to
a trade-off between optimality and computation time.
The main question investigated is, can we learn from past solutions? Can we guide the resolution of
future instances and get faster and better results?
Examples of applications are:
• Unit commitment in energy production
• Project planning
• Assignment problems
• Satellite planning problems
• and standard other Operations Research benchmarks.
The candidate must be enrolled in a university program (Master’s degree or equivalent) to be eligible
The work will involve a fair amount of coding in either C++ or Python and numerical experiments.
There are also many opportunities for research work, depending on the candidate's affinities.
• Majoring in Computer Science or
• Strongly quantitative discipline, with coding experience
• Interest in exploring applications of Machine Learning to Operations Research
• Confidence in programming, (Python and C++ highly desirable),
• Basic Probability and Statistics,
• Basic knowledge of Linear and Integer Programming
Good level in English required, French not necessary.
• A. M. Alvarez, Q. Louveaux, and L. Wehenkel. A machine learning-based approximation of
strong branching. INFORMS Journal on Computing, 29(1):185–195, 2017.
• M. Kruber, M.E. Lübbecke, and Axel Parmantier. Learning when to use a decomposition.
Technical Report 2016–037, Operations Research, RWTH Aachen University, November 2016.
• A. Lodi and G. Zarpellon. On learning and branching: a survey. 2017.
• E. Rachelson, A. B. Abbes, and S. Diemer. Combining mixed integer programming and
supervised learning for fast re-planning. Tools with Artificial Intelligence (ICTAI), 2010.
Associate professor - ISAE Supaero
Dept. of Complex Systems Engineering