Mathieu Dagréou

Ph.D. student in at @Inria_Saclay working on Optimization and Machine Learning @matdag.bsky.social

[Mathieu Dagréou @Mat_Dag]

📣📣 Preprint alert 📣📣

« A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization »

w. @tomamoral, @vaiter & @PierreAblin

https://t.co/OFbY8JQo6e

1/3

[Fabian Schaipp @FSchaipp]

"It's easier to tune the LR for method A than for B."

We tried to formalize this for model-based stochastic optimization methods.

We find a key quantity, called stability index, that describes how stable a (weakly) convex bound is as a function of LR.

📚https://t.co/JIrG0gXqXL

[Michael Arbel @MichaelArbel]

What do JEPA-style self-distillation dynamics actually learn — and why do they sometimes avoid collapse?

In our new work with @BasileTerv987 and Jean Ponce, we tackle this question.

What surprised us: These dynamics provably recover representations with nonlinear-CCA structure.

[Clément Bonet @Clement_Bonet_]

Our work "Busemann Functions in the Wasserstein Space" was accepted at #AISTATS2026

This is a joint work with Elsa Cazelles, Lucas Drumetz and @nicolas_courty.

I will be presenting it tomorrow at the poster 96, see you there!

Link: https://t.co/PYz53som3g

[Mark Schmidt @MarkSchmidtUBC]

This is the way.

[Konstantin Mishchenko @konstmish]

Nesterov dropped a new paper last week on what functions can be optimized with gradient descent.
The idea is simple: we know GD can optimize both nonsmooth (bounded grads) and smooth (Lipschitz grads) functions, but smooth+nonsmooth satisfies neither property, so what can we do?

[Fabian Schaipp @FSchaipp]

🚟 New blog post:

On "infinite" learning-rate schedules and how to construct them from one checkpoint to the next

https://t.co/xa1DS9OTTW

[Rudy Morel @rdMorel]

For evolving unknown PDEs, ML models are trained on next-state prediction. But do they actually learn the time dynamics: the "physics"?

Check out our poster (W-107) at #ICML2025 this Wed, Jul 16. Our "DISCO" model learns the physics while staying SOTA on next states prediction!

[Mathieu Blondel @mblondel_ml]

Back from MLSS Senegal 🇸🇳, where I had the honor of giving lectures on differentiable programming. Really grateful for all the amazing people I got to meet 🙏 My slides are here https://t.co/fWH9FJ7ELm

[Waïss Azizian @wazizian]

❓ How long does SGD take to reach the global minimum on non-convex functions?
With @FranckIutzeler, J. Malick, P. Mertikopoulos, we tackle this fundamental question in our new ICML 2025 paper: "The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes"

[Konstantin Mishchenko @konstmish]

I want to address one very common misconception about optimization. I often hear that (approximately) preconditioning with the Hessian diagonal is always a good thing. It's not. In fact, finding a good preconditioner is an open problem, which I think deserves more attention.
1/4

[Matthieu Terris @MatthieuTerris]

🧵 I'll be at CVPR next week presenting our FiRe work 🔥

TL;DR: We go beyond denoising models in PnP with more general restoration (e.g. deblurring) models!

A starting point observation is that images are not fixed-points of restoration models:

[Samuel Vaiter @vaiter]

📣 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.

https://t.co/81C9BGRtko 1/5

[Mathurin Massias @mathusmassias]

It was received quite enthusiastically here so time to share it again!!!

Our #ICLR2025 blog post on Flow M atching was published yesterday : https://t.co/2V5BLl6T2p

My PhD student Anne Gagneux will present it tomorrow in ICLR, 👉poster session 4, 3 pm, #549 in Hall 3/2B 👈

[Gabriel Peyré @gabrielpeyre]

Optimization algorithms come with many flavors depending on the structure of the problem. Smooth vs non-smooth, convex vs non-convex, stochastic vs deterministic, etc. https://t.co/k1KOSFfSUJ

[Alex Hägele @haeggee]

A really fun project to work on. Looking at these plots side-by-side still amazes me! How well can **convex optimization theory** match actual LLM runs?

My favorite points of our paper on the agreement for LR schedules in theory and practice: 1/n

[Fabian Schaipp @FSchaipp]

Learning rate schedules seem mysterious?
Turns out that their behaviour can be described with a bound from *convex, nonsmooth* optimization.

Short thread on our latest paper 🚇

https://t.co/DGHoG1FS3f

[Konstantin Mishchenko @konstmish]

Learning rate schedulers used to be a big mistery. Now you can just take a guarantee for *convex non-smooth* problems (from https://t.co/2RggKkvmxO), and they give you *precisely* what you see in training large models.
See this empirical study:
https://t.co/kXOOeygaal
1/3

[Theo Uscidda @theo_uscidda]

Our work on geometric disentangled representation learning has been accepted to ICLR 2025! 🎊See you in Singapore if you want to understand this gif better :)

[Gabriel Peyré @gabrielpeyre]

The Mathematics of Artificial Intelligence: In this introductory and highly subjective survey, aimed at a general mathematical audience, I showcase some key theoretical concepts underlying recent advancements in machine learning. https://t.co/FdxBkdLYrw

[Francis Bach @BachFrancis]

My book is (at last) out, just in time for Christmas!
A blog post to celebrate and present it: https://t.co/ttRo04efDF