Sabitlenmiş Tweet
Today's blog post deals with the (non-)differentiability of Dynamic Time Warping.
rtavenar.github.io/blog/softdtw.h…
Feedback is, once again, very welcome!
GIF
English
Romain Tavenard
509 posts
Romain Tavenard
@rtavenar
Prof. @UnivRennes_2. ML for time series. Maintainer of #tslearn package
Rennes, France Katılım Ağustos 2016
157 Takip Edilen370 Takipçiler
Romain Tavenard retweetledi
📣 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
English
Come work with us on tslearn in beautiful Rennes!
(deadline for application is soon!)
jobs.inria.fr/public/classic…
English
Romain Tavenard retweetledi
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
English
Romain Tavenard retweetledi
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 :)
English
Romain Tavenard retweetledi
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)
Nicolas Keriven@n_keriven
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
English
Romain Tavenard retweetledi
Cool work on a differentiable variant of dynamic time warping by @rtavenar
rtavenar.github.io/blog/softdtw.h…
English
Romain Tavenard retweetledi
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. #page=115" target="_blank" rel="nofollow noopener">math.univ-lyon1.fr/~santambrogio/…
English
Romain Tavenard retweetledi
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/~carlier/Breni…
English
Romain Tavenard retweetledi
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.
English
Romain Tavenard retweetledi
Congratulations to Dr. Dagréou @Mat_Dag for a brillant PhD defense! @tomamoral, @PierreAblin and I were lucky to have you as a student.
English
Romain Tavenard retweetledi
🏆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 👩💻
École normale supérieure | PSL@ENS_ULM
#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 !!! 👏
English
Romain Tavenard retweetledi
🚨 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
English
Romain Tavenard retweetledi
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 🧵⬇️
Oussama Zekri@oussamazekri_
🚀 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/🧵
English
Romain Tavenard retweetledi
Large Language Models as Markov Chains ift.tt/uPbQTkA
Français
Romain Tavenard retweetledi
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
English
Romain Tavenard retweetledi
🤗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!
English
Romain Tavenard retweetledi
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
GIF
English
Romain Tavenard retweetledi
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.
Français
Romain Tavenard retweetledi
🎤 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 📢
English