Teaching

École Polytechnique

Master Data Science For Business (X/HEC)

• Python for data science (2021)

Hands on programming lectures where students learn by doing. Teaching style from the tried and tested software carpentry project.

Master data science (X/Télécom Paris/ENSAE)

• Statistical learning theory (2022, 2023)

Mathematical foundations for supervised learning

• Optimization for machine learning (2023)

General overview of optimization in data science: convex, non-convex, smooth and non smooth machine learning models. Theoretical study and practical Python implementation of optimization solvers.

Télécom Paris

Cycle ingénieur (4ème année)

• Advanced Statistics (2022, 2023)

Theoretical course on non-parametric models

• Numerical calculus and Monte-Carlo methods (2022, 2023)

Approximation theory and simulation algorithms

Master spécialisé Big Data AI

• Advanced machine learning (2022, 2023)

Lectures on optimal transport, semi-supervised and self-supervised learning.

Télécom Executive Education

• Introduction to Machine learning (2022, 2023)

Dense 2-day program for executives with little to no previous background in AI.

ENSAE / Sorbonne Université [Teaching assistant during PhD]

• Optimisation différentiable (2017-2020) - ENSAE 1A
• Probability theory (2018) - ENSAE 1A
• Monte-Carlo methods (2017-2020) - ENSAE 2A
• Programmation en C - La Sorbonne Université (2017)