About the seminar

This seminar aims to increase the links between the different laboratories in Saclay in the field of Applied Maths, Statistics and Machine Learning. The Seminar is organized every first Tuesday of the month with 2 presentations followed by a small refreshment. The localization of the seminar will change to accommodate the different labs.

Organization

Due to access restriction, you need to register for the seminar. A link is provided in the description and should also be sent with the seminar announcement. It will also help us organize for the food quantities. If you think you will come, please register! (even if you are unsure)

To not miss the next seminar, please subscribe to the announcement mailing list subscribe/palaisien.
You will receive email on the palaisien@inria.fr mailing list.
You can also add the calendar from the seminar to your own calendar (see below).

Next seminars

REGISTER 01 Dec 2026, 12h At Inria Saclay - Amphi Sophie Germain
TBA
TBA
Tony Bonnaire - Generalization and memorization in Diffusion Models
Diffusion models have emerged as powerful generative tools, capable of producing highly realistic images, videos, and audio by learning a stochastic mapping from a simple Gaussian distribution. Despite their empirical success, the underlying reasons for their effectiveness remain poorly understood. In this talk, we will give a brief primer on the formalism of diffusion models and then dive into the analysis of a well-defined high-dimensional data distribution—a mixture of two Gaussians-under the
Diffusion models have emerged as powerful generative tools, capable of producing highly realistic images, videos, and audio by learning a stochastic mapping from a simple Gaussian distribution. Despite their empirical success, the underlying reasons for their effectiveness remain poorly understood. In this talk, we will give a brief primer on the formalism of diffusion models and then dive into the analysis of a well-defined high-dimensional data distribution—a mixture of two Gaussians-under the assumption of an optimally trained model. In particular, this analysis reveals the existence of a 'memorization' transition where the trajectories are inevitably attracted to one of the training points and reproduce it exactly. We will then explain why, in practice, diffusion models can still generalize despite this curse, thanks to an implicit regularization mechanism in their training dynamics. These findings are supported by both analytical results on simplified models and large-scale numerical experiments on realistic models and datasets. Finally, we will reconcile these results with ideas from supervised learning, showing that the benign overfitting mechanism is still at work in diffusion models but targets the empirical score rather than the population score.

Scientific Committee

The program and the organization of this seminar is driven by a scientific committee composed of members of the different laboratories in Saclay. The members of the committee are currently:

Funding

This seminar is made possible with financial support of the ENSAE and DataIA.