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 palaisien@inria.fr.
You can also add the calendar from the seminar to your own calendar (see below).

Next seminars

REGISTER 05 Mar 2025, 12h At Inria Saclay - Amphi Sophie Germain
Gabriel Peyré - Diffusion Flows and Optimal Transport in Machine Learning
In this talk, I will review how concepts from optimal transport can be applied to analyze seemingly unrelated machine learning methods for sampling and training neural networks. The focus is on using optimal transport to study dynamical flows in the space of probability distributions. The first example will be sampling by flow matching, which regresses advection fields. In its simplest case (diffusion models), this approach exhibits a gradient structure similar to the displacement seen in ...
In this talk, I will review how concepts from optimal transport can be applied to analyze seemingly unrelated machine learning methods for sampling and training neural networks. The focus is on using optimal transport to study dynamical flows in the space of probability distributions. The first example will be sampling by flow matching, which regresses advection fields. In its simplest case (diffusion models), this approach exhibits a gradient structure similar to the displacement seen in optimal transport. I will then discuss Wasserstein gradient flows, where the flow minimizes a functional within the optimal transport geometry. This framework can be employed to model and understand the training dynamics of the probability distribution of neurons in two-layer networks. The final example will explore modeling the evolution of the probability distribution of tokens in deep transformers. This requires modifying the optimal transport structure to accommodate the softmax normalization inherent in attention mechanisms.
Tom Sanders - Recent Advances in Watermarking
Invisible watermarking robustly embeds binary messages within data. This presentation begins with an introduction to watermarking fundamentals and its applications in copyright protection and Generative AI content detection. The focus will then be on image watermarking, highlighting Watermark Anything, which approaches watermarking as a segmentation task, enabling tamper detection and multiple message hiding, as well as improved robustness. Finally, the presentation explores ...
Invisible watermarking robustly embeds binary messages within data. This presentation begins with an introduction to watermarking fundamentals and its applications in copyright protection and Generative AI content detection. The focus will then be on image watermarking, highlighting Watermark Anything, which approaches watermarking as a segmentation task, enabling tamper detection and multiple message hiding, as well as improved robustness. Finally, the presentation explores text watermarking and sheddes light on its "radioactive" properties, meaning that watermarked text propagates through training, which can help detect model distillation and test-set contamination.
REGISTER 02 Apr 2025, 12h At Inria Saclay - Amphi Sophie Germain
Francois Lanusse - TBA
TBA
TBA
Johannes Hertrich - Importance Corrected Neural JKO Sampling
In order to sample from an unnormalized probability density function, we propose to combine continuous normalizing flows (CNFs) with rejection-resampling steps based on importance weights. We relate the iterative training of CNFs with regularized velocity fields to a proximal mappings in the Wasserstein space. The alternation of local flow steps and non-local rejection-resampling steps allows to overcome local minima and mode collapse for multimodal distributions. The arising model can be ...
In order to sample from an unnormalized probability density function, we propose to combine continuous normalizing flows (CNFs) with rejection-resampling steps based on importance weights. We relate the iterative training of CNFs with regularized velocity fields to a proximal mappings in the Wasserstein space. The alternation of local flow steps and non-local rejection-resampling steps allows to overcome local minima and mode collapse for multimodal distributions. The arising model can be trained iteratively, reduces the reverse Kulback-Leibler (KL) loss function in each step, allows to generate iid samples and moreover allows for evaluations of the generated underlying density. Numerical examples demonstrate the efficiency of our approach.

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.