Clément Bonet
@Clement_Bonet_
Followers
231
Following
450
Media
10
Statuses
40
Postdoctoral researcher at ENSAE interested in Optimal Transport.
Paris, France
Joined January 2021
RT @SibylleMarcotte: In Vancouver for #ICML2025! I'll present our work during oral session 1D at 10:45 tomorrow (Ballroom C), followed by p….
0
3
0
RT @Clement_Bonet_: With Christophe, we will present our work tuesday. 📍Oral: West Ballroom D, Poster: East Exhibition Hall A-B #E-1300.📅….
0
1
0
RT @Clement_Bonet_: 🎉 Happy to share that our work "Flowing Datasets with Wasserstein over Wasserstein Gradient Flows" was accepted at #ICM….
0
23
0
RT @BIRS_Math: Clément Bonet (ENSAE/CREST), Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
0
1
0
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!.
0
1
4
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.
1
0
2
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.
1
0
0
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.
1
0
0
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.
2
0
1
🎉 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 @Korba_Anna!. Link:
1
23
100
RT @lomarchehab: Check out this great work led by @HanlinYu2025 and follow him!. We learn the time score faster and more accurately (in pix….
0
2
0
RT @KempnerInst: If you're at #AISTATS2025, check out the presentation by Jonathan Geuter, in collaboration with @Clement_Bonet_ , @Korba_A….
0
6
0
RT @JmlrOrg: 'Sliced-Wasserstein Distances and Flows on Cartan-Hadamard Manifolds', by Clément Bonet, Lucas Drumetz, Nicolas Courty. https….
0
3
0
RT @TmlrPub: Slicing Unbalanced Optimal Transport. Clément Bonet, Kimia Nadjahi, Thibault Sejourne, Kilian FATRAS, Nicolas Courty. Action….
openreview.net
Optimal transport (OT) is a powerful framework to compare probability measures, a fundamental task in many statistical and machine learning problems. Substantial advances have been made in...
0
2
0
RT @RFlamary: Today something crazy happened. POT has reached 1000 citations (total) 🤩🚀. Very proud to be part of a scientific community th….
0
20
0
RT @JamesTThorn: From Diffusion Models to Schrödinger Bridges . - A shame not to see this NeurIPS keynote live, by the incredible @ArnaudDo….
0
23
0
RT @theo_uscidda: Excited about Wasserstein gradient flows? We extend mirror and preconditioned gradient descent on the space of probabilit….
0
9
0
We use Mirror Descent to minimize the Kullback-Leibler divergence with a Gaussian target. With a well chosen potential energy or the entropy as Bregman potential, the algorithm converges faster than the forward backward algorithm.
1
0
2