Yann Traonmilin
@ytraonmilin.bsky.social
CNRS researcher at Institut de mathématiques de Bordeaux.
yanntraonmilin.perso.math.cnrs.fr
yanntraonmilin.perso.math.cnrs.fr
Pinned
Yann Traonmilin
@ytraonmilin.bsky.social
· Jan 23
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 ?
What is the "best" way to estimate elements of a low-dimensional model from a limited number of measurements ?
Reposted by Yann Traonmilin
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
Calliopé
tinyurl.com
February 6, 2026 at 7:56 AM
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
Reposted by Yann Traonmilin
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...
Details at www.ens-lyon.fr/LIP/images/P...
www.ens-lyon.fr
February 5, 2026 at 9:04 AM
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...
Details at www.ens-lyon.fr/LIP/images/P...
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
↓
↓
January 23, 2026 at 8:05 AM
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
↓
↓
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/abs/2509.20511
In this work,...
↓
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...
arxiv.org
January 22, 2026 at 1:26 PM
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/abs/2509.20511
In this work,...
↓
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
Dates & infos :
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.
wmathsia2026.sciencesconf.org
January 19, 2026 at 8:29 AM
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
Dates & infos :
wmathsia2026.sciencesconf.org
Reposted by Yann Traonmilin
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**.
Les inscriptions sont ouvertes jusqu'au 1 mars (majoration > 9/02). La deadline pour soumettre une communication est le **15 janvier**.
December 15, 2025 at 8:11 AM
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**.
Les inscriptions sont ouvertes jusqu'au 1 mars (majoration > 9/02). La deadline pour soumettre une communication est le **15 janvier**.
New (updated) preprint: Stochastic Orthogonal Regularization for deep projective priors, A. Joundi, YT, A. Newson. hal.science/hal-05069394v2
Geometry x deep priors x inverse problems = 👍
↓
Geometry x deep priors x inverse problems = 👍
↓
December 9, 2025 at 3:55 PM
New (updated) preprint: Stochastic Orthogonal Regularization for deep projective priors, A. Joundi, YT, A. Newson. hal.science/hal-05069394v2
Geometry x deep priors x inverse problems = 👍
↓
Geometry x deep priors x inverse problems = 👍
↓
Reposted by Yann Traonmilin
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/
All infos here: nkeriven.github.io/malaga/
MALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG)
nkeriven.github.io
November 6, 2025 at 1:56 PM
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/
All infos here: nkeriven.github.io/malaga/
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.
Interested, if anyone has a reference to a complete solution to this.
October 24, 2025 at 3:09 PM
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.
Interested, if anyone has a reference to a complete solution to this.
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. ?
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. ?
October 16, 2025 at 7:13 AM
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. ?
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. ?
Reposted by Yann Traonmilin
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).
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).
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).
mode2026.sciencesconf.org
October 14, 2025 at 11:28 AM
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).
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).
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/
↓
"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/
↓
October 10, 2025 at 7:37 AM
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/
↓
"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/
↓
"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.
↓
I agree but to be fair to optimization folks, this is generally done by setting up a loss that should guarantee low test error.
↓
Optimization theory has a few important lessons for machine learning, but the list of actionable lessons is surprisingly short.
Minimal Theory
What are the most important lessons from optimization theory for machine learning?
www.argmin.net
October 8, 2025 at 7:20 AM
"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.
↓
I agree but to be fair to optimization folks, this is generally done by setting up a loss that should guarantee low test error.
↓
Reposted by Yann Traonmilin
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)
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)
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...
werkenbij.uva.nl
October 7, 2025 at 11:48 AM
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)
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)
Reposted by Yann Traonmilin
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?
Universal Cascades
A little approximation theory goes a long way
www.argmin.net
September 30, 2025 at 2:31 PM
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?
Reposted by Yann Traonmilin
#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.
Stéphane Mallat, a pioneer bridging mathematics and computer science
news.cnrs.fr
September 11, 2025 at 12:02 PM
#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.
Trying now to find out which LLM is the most "bourbakist"
July 22, 2025 at 12:29 PM
Trying now to find out which LLM is the most "bourbakist"
Reposted by Yann Traonmilin
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/...
July 15, 2025 at 3:35 AM
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/...
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
texture". He gave very nice contributions with modern methods on a challenging ill-posed problem.
antoineguennec.perso.math.cnrs.fr
July 9, 2025 at 7:34 AM
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
texture". He gave very nice contributions with modern methods on a challenging ill-posed problem.
antoineguennec.perso.math.cnrs.fr
Reposted by Yann Traonmilin
The NeurIPS paper checklist corroborates the bureaucratic theory of statistics.
Standard error of what now?
The NeurIPS checklist corroborates the bureaucratic theory of statistics.
www.argmin.net
July 3, 2025 at 2:40 PM
The NeurIPS paper checklist corroborates the bureaucratic theory of statistics.
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 😇)
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 😇)
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 ...
hal.science
May 23, 2025 at 7:18 AM
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 😇)
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 😇)
Reposted by Yann Traonmilin
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
La version en anglais est sur arxiv
arxiv.org/abs/2501.10465
May 16, 2025 at 10:35 PM
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
La version en anglais est sur arxiv
arxiv.org/abs/2501.10465
Solution to all your problems: latex + GIT (or SVN, etc ... ) + clear task distribution 😀
May 14, 2025 at 12:35 PM
Solution to all your problems: latex + GIT (or SVN, etc ... ) + clear task distribution 😀
Reposted by Yann Traonmilin
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
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!
Mathematical Aspects of Data Science
Graduate Summer School - EPFL - Sept. 1-5, 2025
mathsdata2025.github.io
April 14, 2025 at 5:00 PM
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
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!