Mathieu Dagréou
@Mat_Dag
Followers
493
Following
1K
Media
10
Statuses
382
Ph.D. student in at @Inria_Saclay working on Optimization and Machine Learning @matdag.bsky.social
Paris, France
Joined July 2019
📣📣 Preprint alert 📣📣. « A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization ». w. @tomamoral, @vaiter & @PierreAblin. 1/3.
arxiv.org
Bilevel optimization problems, which are problems where two optimization problems are nested, have more and more applications in machine learning. In many practical cases, the upper and the lower...
2
15
43
RT @mblondel_ml: Back from MLSS Senegal 🇸🇳, where I had the honor of giving lectures on differentiable programming. Really grateful for all….
github.com
Slides for the book "The Elements of Differentiable Programming". - diffprog/slides
0
20
0
RT @wazizian: ❓ How long does SGD take to reach the global minimum on non-convex functions?. With @FranckIutzeler, J. Malick, P. Mertikopou….
0
72
0
RT @konstmish: I want to address one very common misconception about optimization. I often hear that (approximately) preconditioning with t….
0
16
0
RT @MatthieuTerris: 🧵 I'll be at CVPR next week presenting our FiRe work 🔥. TL;DR: We go beyond denoising models in PnP with more general r….
0
5
0
RT @mathusmassias: It was received quite enthusiastically here so time to share it again!!! . Our #ICLR2025 blog post on Flow M atching wa….
0
5
0
RT @gabrielpeyre: Optimization algorithms come with many flavors depending on the structure of the problem. Smooth vs non-smooth, convex vs….
0
104
0
RT @FSchaipp: Learning rate schedules seem mysterious?.Turns out that their behaviour can be described with a bound from *convex, nonsmooth….
arxiv.org
We show that learning-rate schedules for large model training behave surprisingly similar to a performance bound from non-smooth convex optimization theory. We provide a bound for the constant...
0
26
0
RT @konstmish: Learning rate schedulers used to be a big mistery. Now you can just take a guarantee for *convex non-smooth* problems (from….
0
76
0
RT @theo_uscidda: Our work on geometric disentangled representation learning has been accepted to ICLR 2025! 🎊See you in Singapore if you w….
0
18
0
RT @gabrielpeyre: The Mathematics of Artificial Intelligence: In this introductory and highly subjective survey, aimed at a general mathema….
0
438
0
RT @BachFrancis: My book is (at last) out, just in time for Christmas!.A blog post to celebrate and present it: htt….
0
318
0
RT @PierreAblin: 🍏🍏🍏 Come work with us at Apple Machine Learning Research! 🍏🍏🍏. Our team focuses on curiosity-based, open research. We wor….
0
36
0
RT @inria_paris: 🏆 #Distinction | Toutes nos félicitations à @gerardbiau (Centre @Inria @Sorbonne_Univ_), directeur de #SCAI et spécialiste….
0
8
0
RT @vaiter: There exists f:[0,1]→[0,1] strictly increasing, continuous function such that its derivative is 0 almost everywhere. https://t.….
0
42
0
RT @GaelVaroquaux: Merci @lemondefr pour un joli résumé de mes aventures scientifiques et logiciels 📈📠 .Beaucoup de….
lemonde.fr
L’informaticien et chercheur à l’Inria est l’expert français le plus cité dans les publications scientifiques portant sur l’IA. Avec Scikit-learn, un programme de machine learning dont il est le...
0
37
0
RT @theo_uscidda: Curious about the potential of optimal transport (OT) in representation learning? Join @CuturiMarco's talk at the UniReps….
0
28
0