For my Ph.D., my research is in applied machine learning,
focussed on low-cost online learning algorithm with
limited feedback (bandit feedback),
mainly applied to cognitive radio problems for
Opportunistic Spectrum Access and setting up reliable network access protocol
for the future Internet of Things networks.
By studying and applying classical and recent Multi-Armed Bandit algorithms
to carefully designed radio models, we are able to prove some performance guarantees,
both numerically in simulations and theoretically with statistical proofs.
2 Research Articles
1 Research Software
(and a lot of personal projects)
3 Research Talks and Posters
2 PhD Advisors
and 1 collaboration with another PhD student
2 Higher Education institutes where I teach in Rennes
International peer-reviewed journals
L. Besson, E. Kaufmann & C. Moy.
Aggregation of Multi-Armed Bandits learning algorithms for Opportunistic Spectrum Access.
[ PDF (not yet) ]
R. Bonnefoi, L. Besson, C. Moy, E. Kaufmann & J. Palicot.
Multi-Armed Bandit Learning in IoT Networks and non-stationary settings.
CrownCom, Lisboa, Portugal.
Best Paper Award!
[ PDF ]
[ Slides ]
[ Poster ]
• [ HAL ]
• [ BibTeX ]
• [ Code (LaTeX) ]
• [ DOI (not yet) ]
L. Besson, J. Fageot, M. Unser.
A theoretical study of steerable homogeneous operators, and applications.
Research Internship Report – Master MVA.
Internship with Prof.Dr. Michael Unser and Dr. Julien Fageot
BIG team at EPFL, Lausanne (Switzerland).
[ PDF ]
[ Slides ]
• [ Code ]
• [ Rank: 1st & Grade: 20/20 ]
My wish is to become a tenured full-time teaching professor
in a Prepatory School in France, in computer science and/or maths.
Ideally, I will be the happiest man on earth if I could
spend the next 30 years teaching introductory Computer Science,
Python (and the next awesome languages) and algorithmics.
ENS de Rennes, Rennes, France :
"préparation à l'agrégation",
with notebooks in Python and OCaml.
(40 h / year)
ENSAI, Rennes, France :
calculability and complexity theory with Turing Machines
(24 h / year).
various teaching and scientific resources,
many Jupyter notebooks,
and some slides.
Written regularly, covering various subjects.
Lots of geeky stuff in English, but teaching resources are in French.
Lycée Lakanal, Sceaux, France :
maths oral exams and Computer Science practical sessions
(110 h / year).
Mahindra Ecole Centrale, Hyderabad, India :
full-time teaching assistant for 2 maths courses and 1 Computer Science course,
(250 h / year).
Correction Rue Ulm, Paris, France :
one-to-one teaching assistant for junior high maths (30 h / year),
and grading of maths written exams (10 times / year).
I love to program and write code and documentation ,
especially in Python for science, GNU Bash for desktop automation, and HTML/CSS/JS for the web.
Everything I did and do is open-source and published,
on my GitHub
profiles. Here are a few things I did since 2012:
World tour timeline
D3.js visualization of a globe, for each country I have ever been to.
small Python and Julia library to efficiently compute the Lempel-Ziv complexity between two binary strings. Published on Pypi
self-spying software for GNU/Linux, with zero CPU overhead and outstanding visualizations.
Since 2012 :
is open-source and publically available, self hosted.