Benjamin Larrousse

Personal webpage

Welcome! I'm Benjamin.

Science passionate, I love how mathematics can help us understand our everyday life, and how, with the right tools, we can make the world a better place. I studied some of them, and in particular optimization and game theory.

I earned a Ph.D. degree in Applied Mathematics, at the Laboratoire des signaux et systèmes in Paris, France. I was working on applying optimization techniques (from Game Theory and Information Theory) to telecommunication problems.

But my Phd in applied mathematics was only the beginning of the journey. I am currently a Senior Data Scientist at Ysance, working with an amazing team.
Currently, my main focus are: Data analysis, machine learning, deep learning, sports analytics, quantified self.


Phd Thesis

International Journal Papers

  1. B. Larrousse, S. Lasaulce, and M. Bloch, "Coordination in distributed networks. Application to power control", submitted to IEEE Transaction on Information Theory (Oct. 2014). [arXiv]

  2. O. Beaude, B. Larrousse, and S. Lasaulce, "Strategic communications in smart grids", to be submitted to IEEE Transactions on Signal Processing.

International Conference Papers

  1. A. Agrawal, F. Danard, B. Larrousse, and S. Lasaulce, Implicit coordination in two-agent team problems, European Conference on Control (ECC), Linz, Austria, July 2015.

  2. B. Larrousse, S. Lasaulce, and M. Wigger, "Coordination in state-dependent distributed networks: The two-agent case", IEEE International Symposium on Information Theory (ISIT), Hong Kong, June 2015. [arXiv]

  3. B. Larrousse, S. Lasaulce, and M. Wigger, Coordinating Partially-Informed Agents over State-Dependent Networks, IEEE Proc. of the Information Theory Workshop (ITW), Jerusalem, Israel, Apr.-May 2015.

  4. B. Larrousse, A. Agrawal, and S. Lasaulce, Implicit coordination in 2-agent team problems. Application to distributed power allocation, IEEE 12th Intl. Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt), Hammamet, Tunisia, May 2014. [Slides]

  5. B. Larrousse, O. Beaude, and S. Lasaulce, Crawford-Sobel Meets Lloyd-Max on the Grid, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014. [BIB] [Slides]

  6. B. Larrousse and S. Lasaulce, Coded Power Control: Performance Analysis, IEEE Intl. Symposium on Information Theory (ISIT), Istanbul, Turkey, Jul. 2013. [BIB] [Slides]

National Conference Papers

  1. O. Beaude, F. Danard, B. Larrousse, and S. Lasaulce, Quantification en présence de divergence d'intérêts : application aux réseaux d'électricité intelligents, Gretsi conference, Lyon, France, Sep. 2015.


Statsbomb Innovation in Football Conference

One of the 8 research competition winners for the first Innovation in Football Conference 2019 by Statsbomb.
Full paper: Improving decision making for shots

PSG and Ecole Polytechnique: Sports Analytics Challenge

Participation with a focus on applying deep learning algorithm to Football data. Ranking: 20/3000+
Here is the link to my blog post explaining my methodology: How Deep Learning can be used in a Football context

Runkeeper data analysis

I use Runkeeper app to track my running sessions since 2012. As it is quite easy to download my personal data, I decided to do a descriptive analysis of my running data.
Jupyter notebook (in Python) can be found here: Runkeeper data analysis

Teaching activities

When I was a Phd student, I also worked as a teaching assistant.
Here is the list of courses I teached at Université Paris 1 Panthéon-Sorbonne :

  • 2012-2015 (Second Semester: 36 hours/year): Quantitative management techniques, organized by Thierry Lafay.
    Level: Undergraduate-Licence 3. Second semester.
    Topics: Logic, linear optimization, game theory, cryptography, graph theory.

  • 2011-2015 (First Semester: 36 hours/year): Mathematics for Economists, organized by Thierry Lafay.
    Level: Undergraduate-Licence 2. First semester.
    Topics: linear algebra, multilinear functions, optimization with and without constraints, complex numbers.

  • 2011-2012 (Second Semester: 36 hours/year): Mathematics for Economists, organized by Thierry Lafay.
    Level: Undergraduate-Licence 1. Second semester.
    Topics: linear algebra, matrices, real analysis.