Clément Bonet

We are recruiting four positions connected to Machine Learning, Statistical Learning, and AI for Science in the Applied Mathematics department at École polytechnique. Join our vibrant community at IP Paris and Hi! Paris IA center. List below🧵 tinyurl.com/3jpw9t26

Open position: Monge Assistant Professor (Tenure track) on graph learning and/or LLMs, in the applied math dpt. at École polytechnique. Reduced teaching load, many funding opportunities, good students and academic freedom. Contact me if interested. Deadline March 23rd tinyurl.com/MongeAssista...

#Distinction 🏆| Charlotte Pelletier, lauréate d'une chaire #IUF, développe des méthodes d’intelligence artificielle appliquées aux séries temporelles d’images satellitaires.
➡️ www.ins2i.cnrs.fr/fr/cnrsinfo/...
🤝 @irisa-lab.bsky.social @cnrs-bretagneloire.bsky.social

I'm thrilled to announce that my #ERCStG project **Optinfinite : Efficient infinite-dimensional optimization over measures**
has been accepted. Thank you
@erc.europa.eu !
Many thanks also to @crestumr.bsky.social @ipparis.bsky.social for they support, as well as to my collaborators and friends.

With Christophe, we will present our work tuesday.

📍Oral: West Ballroom D, Poster: East Exhibition Hall A-B #E-1300
📅 Tuesday, July 15th, 4 p.m. for the Oral, and between 4:30 p.m. and 7 p.m for the Poster.

See you there!

We apply this scheme to minimize the MMD with kernels based on the Sliced-Wasserstein distance. And as applications, we flow dataset of images to solve tasks such as transfer learning and dataset distillation.

We leverage this gradient to do optimization over this space. We update each particle using this gradient, and observe several layers of interactions, between the particles and between the classes.

To solve this task, we endow the space with the Wasserstein over Wasserstein (WoW) distance, and exploit its Riemannian structure. It gives us a way to define a notion of gradient.

In our work, we propose to model labeled datasets as probability over probability distributions, and to frame the task of flowing datasets as a minimization of a discrepancy over this space.

🎉 Happy to share that our work "Flowing Datasets with Wasserstein over Wasserstein Gradient Flows" was accepted at #ICML2025 as an oral!

This is a joint work with the amazing Christophe Vauthier and @akorba.bsky.social !

Link: openreview.net/forum?id=I1O...

DDEQs: Distributional Deep Equilibrium Models through Wasserstein... Deep Equilibrium Models (DEQs) are a class of implicit neural networks that solve for a fixed point of a neural network in their forward pass. Traditionally, DEQs take sequences as inputs, but have...

If you're at #AISTATS2025, check out the presentation by Jonathan Geuter, in collaboration with Clément Bonet, @akorba.bsky.social and @dmelis.bsky.social.

'DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows'

openreview.net/forum?id=rFf...

#AI #statistics #ML

Solutions to the PAWL problem in 1D for different amounts of mass to be transported

⚔️ One for all and all for one ⚔️
Efficient computation of PArtial Wasserstein distances on the Line (PAWL)

is accepted to @iclr-conf.bsky.social

Joint work with Laetitia Chapel: we introduce an 𝑂(𝑛 𝑙𝑜𝑔 𝑛) solver for partial Optimal Transport (OT) in 1D

openreview.net/forum?id=kzE...

🧵 1/2

Slicing Unbalanced Optimal Transport

Clément Bonet, Kimia Nadjahi, Thibault Sejourne, Kilian FATRAS, Nicolas Courty

Action editor: Benjamin Guedj

https://openreview.net/forum?id=AjJTg5M0r8

#transport #outliers #optimal

The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...

Google scholar extract with 1000 citation for POT Python Optima; Transport

Today something crazy happened. POT has reached 1000 citations (total) 🤩🚀. Very proud to be part of a scientific community that acknowledges open source research software. Please continue to use, cite and contribute to POT ! Small🧵below for those interested pythonot.github.io

Live! Keynote talk by Arnaud Doucet
From Diffusion Models to Schrödinger Bridges
West Exhibition Hall C, B3
https://buff.ly/4ga9GD7

Mirror and Preconditioned Gradient Descent in Wasserstein Space As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on $\mathbb{R}^d$ have received their counterpart...

Glad to announce that our work "Mirror and Preconditioned Gradient Descent in Wasserstein Space" was accepted at #NeurIPS2024 as a spotlight!

This is a joint work with the amazing T. Uscidda, A. David, P.C. Aubin-Frankowski and A. Korba!

Link: arxiv.org/abs/2406.08938