Make sure to go check our work (Oscar will be presenting it) if you are going to AISTATS ! virtual.aistats.org/virtual/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/... 😅

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.

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

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

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...

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,... ↓

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

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**.

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 = 👍 ↓

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/

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.

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. ?

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).

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/ ↓

"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 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)

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?

#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"

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

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 😇)

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

Solution to all your problems: latex + GIT (or SVN, etc ... ) + clear task distribution 😀

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!

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

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 !

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/...

My thoughts today about my GPT loving students: how are you going to calculate a Fourier Transform on a desert island ?

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 ... ↓

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 ↓

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 !

🎓 💫 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

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 ?