Sign in

Yann Traonmilin

@ytraonmilin.bsky.social
45 followers 80 following 62 posts

CNRS researcher at Institut de mathématiques de Bordeaux. yanntraonmilin.perso.math.cnrs.fr

PostsRepliesMedia
Yann Traonmilin @ytraonmilin.bsky.social · 24/09/2026
Accepted in ACHA authors.elsevier.com/a/1nqIA3nqGV... hal.science/hal-04725337/ This work on optimal algorithms for inverse problems started a few years ago and led to many things. The path was interesting starting with: what is the best way to solve ill-posed inverse problems ?
authors.elsevier.com
100
Yann Traonmilin @ytraonmilin.bsky.social · 17/09/2026
I have a proposition to settle this matter: Solving problems is only a tool and proxy for achieving the primary goal of conceptual understanding and insight for solving problems.
010
Reposted by Yann Traonmilin
Timothy Gowers @wtgowers.bsky.social · 17/09/2026
I've written a blog post responding to the letter about maths and AI signed by 25 Fields medallists. As with the Leiden Declaration, I didn't sign it, but I agree with much of it and welcome its existence. gowers.wordpress.com/2026/09/17/w...
gowers.wordpress.com
Why I didn’t sign the Fields medallists’ letter
When I was around 11 I heard for the first time about Fermat’s Last Theorem. I was immediately captivated by the problem statement, as well as by the accompanying story, and made a fairly ser…
45523
Yann Traonmilin @ytraonmilin.bsky.social · 09/09/2026
Food for thought: Si je prend une estimation grossière du prix du résultat sur NS, disons 10M$ (comme j'ai pu voir, sans compter l'entrainement) ça fait grosso modo 200 ans équivalent - chercheur CNRS, mobilisés en quelques jours sur un sujet précis.
111
Yann Traonmilin @ytraonmilin.bsky.social · 31/08/2026
La deadline approche, n'hésitez pas à proposer une contribution !
010
Yann Traonmilin @ytraonmilin.bsky.social · 28/05/2026
Accepted to SIAM Journal on Imaging Sciences. Congrats Ali ! Next step: PhD defense !
100
Yann Traonmilin @ytraonmilin.bsky.social · 20/05/2026
L'appel à contribution du workshop sur les maths de l'IA (4-6 nov. 2026) à Bordeaux est ouvert ! Il suffit de suivre les instructions sur : wmathsia2026.sciencesconf.org?lang=fr avec le soutien de l'Institut de mathématiques de Bordeaux, du PEPR PDE-AI, du RT MAIAGES , et du groupe SMAI-MODE.
wmathsia2026.sciencesconf.org
Workshop sur les mathématiques de l'IA - Sciencesconf.org
102
Yann Traonmilin @ytraonmilin.bsky.social · 27/04/2026
Make sure to go check our work (Oscar will be presenting it) if you are going to AISTATS ! virtual.aistats.org/virtual/2026...
virtual.aistats.org
AISTATS Poster A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior AlgorithmAISTATS 2026
001
Yann Traonmilin @ytraonmilin.bsky.social · 08/04/2026
Was wondering why we call sampling theorem "Shannon-Nyquist" theorem as it is a quite direct application of the Poisson formula, learned that the formula is from Cauchy who himself aknowledges Euler culturemath.ens.fr/thematiques/... 😅
culturemath.ens.fr
Le théorème d’échantillonnage. . . de Shannon?
Le théorème d'échantillonnage, souvent appelé théorème de Shannon, constitue une des bases du domaine du traitement de l'information. Mais Shannon lui-même ne s'en attribue pas le mérite et effectivem...
031
Yann Traonmilin @ytraonmilin.bsky.social · 23/03/2026
We got best paper award at CPAL. I am sure Ali will do a great job at presenting this work. There are some quite interesting insights in this work.
011
Yann Traonmilin @ytraonmilin.bsky.social · 02/03/2026
We uploaded "A note on the convergence of RED algorithms under minimal hypotheses and open questions" hal.science/hal-05528679 . There is a little result in relation to my latest works with deep projective priors that brings some questions. I found myself talking about this with
hal.science
A note on the convergence of RED algorithms under minimal hypotheses and open questions
In this note, we give a convergence result for a modified "regularization-by-denoising"(RED) algorithm under a restricted isometry condition on measurements and a restricted Lipschitz condition on the considered deep projective prior. This study leads to open questions about the convergence of RED algorithms.
100
Reposted by Yann Traonmilin
Rémi Flamary @rflamary.bsky.social · 06/02/2026
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
tinyurl.com
Calliopé
11218
Reposted by Yann Traonmilin
Mathurin Massias @mathurinmassias.bsky.social · 05/02/2026
There is an Associate Professor position in CS at ENS Lyon, with potential integration in my team, starting in sept 2026: DM me in interested! Details at www.ens-lyon.fr/LIP/images/P...
ens-lyon.fr
078
Yann Traonmilin @ytraonmilin.bsky.social · 23/01/2026
Good week ! Our paper with A. Joundi and J.-F. Aujol "From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent" hal.science/hal-05401157v1 has been accepted to conference on Parsimony and Learning ↓
120
Yann Traonmilin @ytraonmilin.bsky.social · 22/01/2026
Our work with O. Leong "A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm" has been accepted to AISTATS2026. arxiv.org/abs/2509.20511 In this work,... ↓
arxiv.org
A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm
Recovering high-dimensional signals from corrupted measurements is a central challenge in inverse problems. Recent advances in generative diffusion models have shown remarkable empirical success in pr...
110
Yann Traonmilin @ytraonmilin.bsky.social · 19/01/2026
Save the date : on organise un workshop sur les maths de l'IA à Bordeaux les 4-6 novembre. N'hésitez pas ! plus on est de fous plus on rit ! (dans les limites des capacités d'accueil haha) Dates & infos : wmathsia2026.sciencesconf.org
wmathsia2026.sciencesconf.org
Workshop sur les mathématiques de l'IA - Sciencesconf.org
Le workshop se déroulera sous forme de présentations sur appel à contribution (résumé d'une page). Une session poster sera organisée au besoin selon le nombre de contributions.
1136
Reposted by Yann Traonmilin
Samuel Vaiter @samuelvaiter.com · 15/12/2025
Les inscriptions aux journées MODE 2026 à Nice sont désormais ouvertes. Elles se dérouleront du 18 au 20 mars à l'Hôtel Saint-Paul. Les inscriptions sont ouvertes jusqu'au 1 mars (majoration > 9/02). La deadline pour soumettre une communication est le **15 janvier**.
157
Reposted by Yann Traonmilin
Nicolas Keriven @nicolaskeriven.bsky.social · 06/11/2025
I have several offers for Master internships / PhDs on graph ML funded by ERC MALAGA for 2026. Don't hesitate to contact me to apply! All infos here: nkeriven.github.io/malaga/
nkeriven.github.io
MALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG)
088
Yann Traonmilin @ytraonmilin.bsky.social · 24/10/2025
Fun friday night problem: consider a random variable X with distribution p and a random variable Y such that X+Y has distribution p, what can you say about the distribution of Y ? Interested, if anyone has a reference to a complete solution to this.
100
Yann Traonmilin @ytraonmilin.bsky.social · 16/10/2025
Math in elementary school, definitions: aligned points: points lying on a line line: an infinity of aligned points points alignés : points appartenant à la même droite droite: infinité de points alignés 🤔 I'm still stuck in a loop 🤣 What would be a good definition of line for 7 y.o. ?
220
Reposted by Yann Traonmilin
Samuel Vaiter @samuelvaiter.com · 14/10/2025
Les journées SMAI-MODE 2026 auront lieu à Nice du 18 au 20 mars 2026, précédées par un mini-cours les 16/17. Vous pouvez déposer votre proposition de contrib sur mode2026.sciencesconf.org Inscription à partir du 1er décembre pour finir le 1 mars (avec un tarif majoré à compter du 1 février).
mode2026.sciencesconf.org
Journées SMAI-MODE 2026 - Sciencesconf.org
Du 18 au 20 mars 2025, l'Université Côte d'Azur accueille les journées SMAI-MODE, la conférence biennale du groupe MODE de la Société de Mathématiques Appliquées et Industrielles (SMAI).
144
Yann Traonmilin @ytraonmilin.bsky.social · 10/10/2025
Preprint: improved deterministic error bounds for post-training quantization for CNN architectures. "On the impact of the parametrization of deep convolutional neural networks on post-training quantization", Samy Houache, J.-F. Aujol, Y.T. hal.science/hal-04922698/ ↓
120
Yann Traonmilin @ytraonmilin.bsky.social · 08/10/2025
"But more importantly, we don’t care if you can find a global minimum of the training error. We care if you can find a global minimum of the test error." I agree but to be fair to optimization folks, this is generally done by setting up a loss that should guarantee low test error. ↓
100
Reposted by Yann Traonmilin
Tim van Erven @timvanerven.nl · 07/10/2025
I have 2 open PhD positions on Mathematical Foundations for Explainable AI: Position 1: werkenbij.uva.nl/en/vacancies... (apply by October 13, 2025) Position 2: applications via the Ellis PhD Program: ellis.eu/news/ellis-p... by Oct. 31. Both positions are equivalent (except for starting dates)
werkenbij.uva.nl
Vacancy — PhD Position on Mathematical Foundations for Explainable AI
Are you highly motivated to do PhD research in mathematical machine learning, with special emphasis on mathematical foundations for explainable AI? If yes, the Korteweg-de Vries Institute for Mathemat...
075
Reposted by Yann Traonmilin
Ben Recht @beenwrekt.bsky.social · 30/09/2025
I wrote what are likely some very outdated thoughts on approximation theory. All of this was known in 1990. Which new perspectives am I missing?
argmin.net
Universal Cascades
A little approximation theory goes a long way
041
Yann Traonmilin @ytraonmilin.bsky.social · 22/09/2025
worksinprogress.co/issue/why-sc...
worksinprogress.co
Why science needs outsiders - Works in Progress Magazine
Science has forgotten that the greatest breakthroughs often come from outsiders who are able to take a fresh perspective.
000
Reposted by Yann Traonmilin
CNRS @cnrs.fr · 11/09/2025
#CNRSnews 🗞️ The CNRS mathematician and computer scientist Stéphane Mallat receives the CNRS 2025 Gold Medal for his achievements in applied maths and signal processing, including the JPEG 2000 image compression standard and mathematical foundations of AI.
news.cnrs.fr
Stéphane Mallat, a pioneer bridging mathematics and computer science
04113
Yann Traonmilin @ytraonmilin.bsky.social · 22/07/2025
Trying now to find out which LLM is the most "bourbakist"
020
Reposted by Yann Traonmilin
Bruno Galerne @bgalerne.bsky.social · 15/07/2025
Tommorrow Emile Pierret will present our paper "Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors". #ICML2025 Tue 15 Jul 11 a.m. West Exhibition Hall B2-B3 #W-1015. More details here: pierret.perso.math.cnrs.fr/publication/...
Graphs of Wasserstein errors for various diffusion model samplers
172
Yann Traonmilin @ytraonmilin.bsky.social · 09/07/2025
Congrats Dr Antoine Guennec who defended is PhD thesis yesterday on "Sparse models and deep priors for image decomposition into structure and texture". He gave very nice contributions with modern methods on a challenging ill-posed problem. antoineguennec.perso.math.cnrs.fr
010
Reposted by Yann Traonmilin
Ben Recht @beenwrekt.bsky.social · 03/07/2025
The NeurIPS paper checklist corroborates the bureaucratic theory of statistics.
argmin.net
Standard error of what now?
The NeurIPS checklist corroborates the bureaucratic theory of statistics.
46413
Yann Traonmilin @ytraonmilin.bsky.social · 23/05/2025
Nice two weeks coming: next week "Mathematic of AI workshop" at Institut de mathématiques de Bordeaux In two weeks, presentation on optimal low-dimensional recovery at SMAI 2025 conference smai2025.math.cnrs.fr/fr/ (synchronized with a recent much needed update to hal.science/hal-04725337 😇)
hal.science
Towards optimal algorithms for the recovery of low-dimensional models with linear rates
We consider the problem of recovering elements of a low-dimensional model from linear measurements. From signal and image processing to inverse problems in data science, this question has been at the ...
000
Reposted by Yann Traonmilin
Gabriel Peyré @gabrielpeyre.bsky.social · 16/05/2025
Mon article sur les maths de l’IA est paru dans la gazette de la smf smf.emath.fr/publications... La version en anglais est sur arxiv arxiv.org/abs/2501.10465
0268
Yann Traonmilin @ytraonmilin.bsky.social · 14/05/2025
Solution to all your problems: latex + GIT (or SVN, etc ... ) + clear task distribution 😀
010
Reposted by Yann Traonmilin
Lénaïc Chizat @lenaicchizat.bsky.social · 14/04/2025
Announcing : The 2nd International Summer School on Mathematical Aspects of Data Science mathsdata2025.github.io EPFL, Sept 1–5, 2025 Speakers: Bach @bachfrancis.bsky.social Bandeira Mallat Montanari Peyré @gabrielpeyre.bsky.social For PhD students & early-career researchers Apply before May 15!
mathsdata2025.github.io
Mathematical Aspects of Data Science
Graduate Summer School - EPFL - Sept. 1-5, 2025
14424
Yann Traonmilin @ytraonmilin.bsky.social · 08/04/2025
Très heureux d'organiser en mai une journée de l'IMB "Mathématiques de l'IA" avec une belle diversité thématique: transport optimal, optimisation, matrices aléatoires, problèmes inverses, imagerie médicale... yanntraonmilin.perso.math.cnrs.fr?p=559
yanntraonmilin.perso.math.cnrs.fr
Workshop Mathématiques de l’IA – Yann Traonmilin
000
Yann Traonmilin @ytraonmilin.bsky.social · 27/03/2025
TIL the word (I was looking for): proximinal "A set where the orthogonal projection exists for every external point is called a proximinal set" Strange that I learn it only now !
010
Reposted by Yann Traonmilin
Carola Doerr @caroladoerr.bsky.social · 04/03/2025
Job alert: full-time researcher position for AI with CNRS here in France. Initial contract for 5 years (tenure track). Attractive starting package and better salary than regular positions. I have been w/ @cnrs.fr since 2013, it's great! Applications due 31/03 www.ins2i.cnrs.fr/en/cnrsinfo/...
ins2i.cnrs.fr
Choose France - CNRS AI Rising Talents
As part of the French Strategy in Artificial Intelligence (AI), the Choose France - CNRS AI Rising Talents program offers exceptionally tal
12121
Yann Traonmilin @ytraonmilin.bsky.social · 26/02/2025
My thoughts today about my GPT loving students: how are you going to calculate a Fourier Transform on a desert island ?
021
Yann Traonmilin @ytraonmilin.bsky.social · 19/02/2025
Accepted to SIIMS, congrats Antoine, next Step PhD defense! "Joint structure-texture low dimensional modeling for image decomposition with a plug and play framework" (Guennec, Aujol, YT) hal.science/hal-04648963v1 We describe how structure-texture decomposition is directly linked to ... ↓
100
Yann Traonmilin @ytraonmilin.bsky.social · 18/02/2025
Congrats to Ali Joundi for his paper accepted at SSVM2025 "Max-sparsity atomic autoencoders with application to inverse problems" with YT, A. Newson. hal.science/hal-04773954v1 ↓
110
Yann Traonmilin @ytraonmilin.bsky.social · 12/02/2025
Today had a student using Chatgpt instead of her own notes taken during the lesson to do a python exercise on the Discrete Fourier Transform. The Parseval identity was wrong... Strange to add a part "how to use AI" in my lessons !
130
Reposted by Yann Traonmilin
Gaël Varoquaux @gaelvaroquaux.bsky.social · 29/01/2025
🎓 💫 We are opening post-doc positions at the intersection of AI, data science, and medicine: • Large Language Models for French medical texts • Evaluating digital medical devices: statistics and causal inference
12716
Yann Traonmilin @ytraonmilin.bsky.social · 23/01/2025
Updated preprint: "Towards optimal algorithms for the recovery of low-dimensional models with linear rates" (T., Aujol, Guennec) hal.science/hal-04725337 What is the "best" way to estimate elements of a low-dimensional model from a limited number of measurements ?
131