About me

I am a third-year PhD Student in Machine Learning in the Sierra research team at Inria, where I am co-advised by Julien Mairal and Alexandre d'Aspremont. I also depend on Inria Thoth research team. My PhD focuses on designing data and/or memory efficient learning algorithms, e.g, in natural language processing (NLP), using tools from kernel methods, optimal transport or convex optimization. I am also interested in causality and its interfaces with machine learning. Finally, I am curious about technology and its implications in politics and entrepreneurship. I sometimes write on these subjects for the Group for Geopolitical Studies, a european think-tank hosted at École normale supérieure.

Interests

  • Machine learning (Kernel Methods, Deep Learning)
  • Natural Language Processing
  • Causality
  • Convex Optimization
  • Technology policies and Entrepreneurship

Education

  • PhD in Machine Learning

    Inria

  • MSc in Machine Learning (MVA), 2018

    ENS Paris-Saclay

  • Diplôme d'Ingénieur (Theoretical Physics, Business Studies), 2017

    École polytechnique

  • Research Intern, 2016

    MIT, Department of Nuclear Science and Engineering

News

All news»

[04/02/21] I talked about “How Natural Language Processing is reshaping Machine Learning” at the Paris NLP Meetup.

[12/01/21] Our paper A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention was accepted to ICLR 2021.

[12/12/20] I presented a short version of our paper A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention at the Interpretable Inductive Biases and Physically Structured Learning Workshop, NeurIPS 2020.

[07/01/20] Our paper Screening Data Points in Empirical Risk Minimization was accepted to AISTATS 2020.

[17/12/19] I was involved in a french study on the consequences of automation in commerce and distribution, commissioned by the Prospective Observatory for Trade.

Recent Publications

Recent & Upcoming Talks

Designing Transformers with Kernel Methods
How Natural Language Processing is reshaping Machine Learning

Recent Posts

Notes I wrote (in French) for the Group for Geopolitical Studies.

Le logiciel libre, outil de soft power et de lutte contre le Covid-19

Gustave Ronteix et moi-même avons interrogé Alexandre Gramfort, chercheur en machine learning à Inria Saclay, pour le Grand Continent. Open source comme outil stratégique, naissance de scikit-learn, IA en santé, GAFAs et monde académique : le résultat est passionnant et disponible ici.

Le prix Turing 2019 souligne le retard de l’Europe dans le numérique

La remise des prix Turing adoube les pères fondateurs de l’apprentissage profond, qui a joué un rôle crucial dans la résurgence actuelle de l’intelligence artificielle. Le prix reconnaît aussi dans une certaine mesure l’école de formation européenne en informatique, mais révèle en creux la difficulté de maintenir ces profils en Europe et d’y créer un pôle informatique industriel sur le vieux continent. Signaux faibles du retard de l’Union dans l’intelligence artificielle.

Contact