Joined August 2016
10 Photos and videos
Pinned Tweet
Today's blog post deals with the (non-)differentiability of Dynamic Time Warping. rtavenar.github.io/blog/soft… Feedback is, once again, very welcome!
2
9
42
Romain Tavenard retweeted
📣 New preprint 📣 **Differentiable Generalized Sliced Wasserstein Plans** w/ L. Chapel @rtavenar We propose a Generalized Sliced Wasserstein method that provides an approximated transport plan and which admits a differentiable approximation. arxiv.org/abs/2505.22049 1/5
1
4
30
2,688
Romain Tavenard retweeted
Come work with us on tslearn in beautiful Rennes! (deadline for application is soon!) jobs.inria.fr/public/classic…

7
8
544
Romain Tavenard retweeted
Our @TmlrOrg paper "Gradient scarcity with Bilevel Optimization for Graph Learning" (w/ H Ghanem, @vaiter ) was accepted as an oral presentation at @LogConference 🤓 100% free and online, come check it out! arxiv.org/abs/2303.13964

7
34
2,006
Romain Tavenard retweeted
I have multiple openings for M2 internship / PhD / postdoc in Nice (France) on topics related to bilevel optimization, automatic differentiation and safe machine learning. More details on my webpage samuelvaiter.com Contact me by email, and feel free to forward/RT :)

2
62
121
21,897
Romain Tavenard retweeted
I have several internship/PhD positions on Graph ML available with ERC MALAGA 🤓 See details here: nkeriven.github.io/malaga/ Don't hesitate to contact me! (same if you are interested in a post-doc related to graph ML)

I'm thrilled to announce that my #ERCStG project has been accepted 🤓 **MALAGA: Reinventing the Theory of Machine Learning on Large Graphs** Many job openings coming up, see nkeriven.github.io/malaga for updates! Thank you @ERC_Research and all my collaborators past and future
2
23
128
15,519
Romain Tavenard retweeted
Cool work on a differentiable variant of dynamic time warping by @rtavenar rtavenar.github.io/blog/soft…
5
5
52
4,000
Romain Tavenard retweeted
21 Oct 2024
A Monge map, i.e., a solution to optimal transport Monge problems, may not always exist, be unique, or be symmetric with respect to the source and target distributions. It was one of the motivation to introduce Kantorovich relaxation. math.univ-lyon1.fr/~santambr…
1
24
197
10,242
Romain Tavenard retweeted
17 Oct 2024
Brenier's theorem states that the optimal transport map between two probability measures for quadratic cost is the gradient of a convex function. Moreover, it is uniquely defined up to a Lebesgue negligible set. ceremade.dauphine.fr/~carlie…
1
25
188
11,358
Romain Tavenard retweeted
11 Oct 2024
Bilevel optimization problems with multiple inner solutions come typically in two flavors: optimistic and pessimistic. Optimistic assumes the inner problem selects the best solution for the outer objective, while pessimistic assumes the worst-case solution is chosen.
1
23
182
9,287
Romain Tavenard retweeted
Congratulations to Dr. Dagréou @Mat_Dag for a brillant PhD defense! @tomamoral, @PierreAblin and I were lucky to have you as a student.
3
32
3,646
Romain Tavenard retweeted
🏆Didn't get the Physics Nobel Prize this year, but really excited to share that I've been named one of the #FWIS2024 @FondationLOreal-@UNESCO French Young Talents alongside 34 amazing young researchers! This award recognizes my research on deep learning theory #WomenInScience 👩‍💻
#FWIS2024 🎖️@SibylleMarcotte, doctorante au département #mathématiques et applications de l'ENS @psl_univ, figure parmi les lauréates du Prix Jeunes Talents France 2024 @FondationLOreal @UNESCO #ForWomenInScience @AcadSciences @4womeninscience Félicitations à elle !!! 👏
14
19
323
35,756
Romain Tavenard retweeted
🚨 Interested in domain adaptation and generalization for 3D data? 🚨 It’s tough to keep up with all the new amazing work. That’s why I’ve curated a comprehensive, easy-to-navigate list of publications. 📚 👉 Repo: bit.ly/DA_DG_3D
1
6
12
1,752
Romain Tavenard retweeted
A simple, yet overlooked idea: LLMs with a finite vocabulary and context window are (finite) Markov chains :) An 🤩 internship of @oussamazekri_in collaboration with now officially our 1st year Ph.D. student @AmbroiseOdonnat @abenechehab @bleistein_linus & N. Boullé A 🧵⬇️
🚀 Have you heard about @karpathy ‘s tweet on LLMs and Markov chains? Well, we build on this idea in our newest paper! 🤓 "𝐋𝐚𝐫𝐠𝐞 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥𝐬 𝐚𝐬 𝐌𝐚𝐫𝐤𝐨𝐯 𝐂𝐡𝐚𝐢𝐧𝐬"   📑 arxiv.org/pdf/2410.02724… 1/🧵
4
10
1,112
Romain Tavenard retweeted
Stein's Lemma states that for a normally distributed variable X, the expected value E[Xg(X)] = E[g’(X)] for any g absolutely continuous (derivative a.e.) such that E[|g’(X)|] < ∞. It is a central result for characterizing Gaussian data arxiv.org/abs/2104.08302
3
21
157
9,045
Romain Tavenard retweeted
🤗Officially started Ph.D. with @IevgenRedko, @rtavenar and Laetitia Chapel @Inria @irisa_lab on Transformers & Distribution Shifts 🥳🇨🇦 Also, 2 papers accepted at #NeurIPS2024 📈 *Spotlight* arxiv.org/pdf/2406.10327 ✋🏾 MaNO arxiv.org/pdf/2405.18979 More details soon!
1
8
32
1,409
Romain Tavenard retweeted
I'm thrilled to announce that my #ERCStG project has been accepted 🤓 **MALAGA: Reinventing the Theory of Machine Learning on Large Graphs** Many job openings coming up, see nkeriven.github.io/malaga for updates! Thank you @ERC_Research and all my collaborators past and future
18
23
173
28,921
Romain Tavenard retweeted
Un évènement sur l'IA où je participais a été chamboulé par Extinction Rébellion (mauvaise cible: ça parlait des limites de l'IA). C'est symptomatique du contexte de communication contrôlée ne laissant aux voix dissonantes uniquement une place violente.
1
2
7
2,155
Romain Tavenard retweeted
🎤 Very happy to get to present SAMformer at @CriteoAILab two weeks ago! Thanks again for the invitation @LDosSantos_ and @jy_franceschi 🙏 Slides on my website ambroiseodt.github.io/ Bonus: SAMformer poster session at #icml2024 with @IevgenRedko 📢
1
9
10
1,124