Welcome to my personal webpage!


I have defended my PhD thesis on October 15th, you can find my dissertation, entitled Learning time-dependent data with the signature transform here.

Short bio

I am since November 2021 a postdoctoral researcher at the Center for Computational Biology (CBIO), Mines ParisTech, under the supervision of Chloé-Agathe Azencott, and funded by the PRAIRIE institute.

Previously, I was a PhD student in Statistics at LPSM, Sorbonne Université, under the supervision of Gérard Biau and Benoît Cadre.

You can find my complete CV here: Curriculum Vitae,

Research interests

I am generally interested in the mathematical theory of deep learning, in particular in neural ordinary differential equations, post-selection inference, and learning with time series. The topic of my PhD was the application of signatures, a tool from stochastic analysis that allows to extract information from temporal data, in statistics and machine learning. This subject has been developed in two directions: on the one hand, designing new algorithms using signatures as features, and, on the other hand, leveraging the theory of signatures to study existing deep learning algorithms such as RNN, via the recent notion of neural ordinary differential equations. Check out the DataSig website for more information on applications of signatures in machine learning.