Probabilistic Generative Models

This is the website for the Probabilistic Generative Models course (TC4) of Master 2 AI at Université Paris-saclay.


Recently, generative models have (again) become a hot topic in machine learning thanks to recent advances in deep learning. One of the benefit of these models is their ability to generate new data, see for example:

Moreover, they can be used for semi-supervised learning, feature extraction via latent variables, …

In this course, we will first review the theoretical background required to understand modern generative models (change of variable theorem, reparameterization, MCMC sampling, variational methods, score function estimator…) and then study several types of generative models (sigmoid belief networks, Boltzmann machines, variational auto-encoders, normalizing flows, …).

Grading Scheme

  • 50%: Lab exercises

  • 50%: Exam


You can contact me at, either in French or English, with a subject starting with [PGM]. Please, do not worry about typos or not being overly formal enough (just treat your instructors and colleagues with the same respect you would like to be treated).

WARNING: Each mail must discuss at most one point. Don’t send e-mails to several of my addresses. Thank you