@Sierra_ML_Lab

Twitter account of the Sierra project-team @Inria_Paris, @CNRS, @ENS_ULM #MachineLearning & #Optimization

 Paris
di.ens.fr/sierra/
Joined March 2021
  • Tweets64
  • Following36
  • Followers511
2Media
As the SIERRA team of @inria_paris, we will be presenting 11 papers at @NeurIPSConf 2021 and a Test of Time Award! + Very happy to mention that one of our papers received an Outstanding Paper Award! See the thread below for details + join us at the posters if interested! 1/13
2
9
1
99
What are good optimizers for diffusion models? 🍂 TLDR: Muon and SOAP are very good. Paper: arxiv.org/pdf/2510.19376
7
46
3
325
21,590
Bravo Etienne!
Etienne Gauthier@Gauthier_E_24 Oct 2025
I am honored to be a 2025 Google PhD Fellow in Machine Learning & ML Foundations 🥳 Grateful to @Googleorg for their incredible support, my advisors @BachFrancis & Michael I. Jordan, and my lab at @Inria & @ENS_ULM for fostering a space to think deeply.
1
1
403
I am honored to be a 2025 Google PhD Fellow in Machine Learning & ML Foundations 🥳 Grateful to @Googleorg for their incredible support, my advisors @BachFrancis & Michael I. Jordan, and my lab at @Inria & @ENS_ULM for fostering a space to think deeply.
Google.org
@Googleorg23 Oct 2025
🎉 We're excited to announce the 2025 Google PhD Fellows! @GoogleOrg is providing over $10 million to support 255 PhD students across 35 countries, fostering the next generation of research talent to strengthen the global scientific landscape. Read more: goo.gle/43wJWw8
A person with long hair is seen from behind working in a laboratory

ALT A person with long hair is seen from behind working in a laboratory

9
9
1
126
17,584
Together with the great Frederik Kunstner (fkunstner.github.io)
2
22
3,736
Not all scaling laws are nice power laws. This month’s blog post: Zipf’s law in next-token prediction and why Adam (ok, sign descent) scales better to large vocab sizes than gradient descent: francisbach.com/scaling-laws…
4
49
2
460
29,726
Tired of lengthy computations to derive scaling laws? This post is made for you: discover the sharpness of the z-transform! francisbach.com/z-transform/
2
38
3
271
19,778
Happy to have our recent papers on conformal prediction with e-values presented at COLT by my advisor @BachFrancis! Full details here: 📚arxiv.org/abs/2503.13050 📚arxiv.org/abs/2505.13732 #COLT2025
7
1
68
5,787
For good probability predictions, you should use post-hoc calibration. With @Eugene_Berta, Michael Jordan, and @BachFrancis we argue that early stopping and tuning should account for this! Using the loss after post-hoc calibration often avoids premature stopping. 🧵1/
2
23
2
129
13,037
I’ll be presenting our paper at COLT in Lyon this Monday at the Predictions and Uncertainty workshop — come say hi if you're around! 👋 Check out @DHolzmueller's thread below 👇 #COLT2025
David Holzmüller @ ICML 2026@DHolzmueller27 Jun 2025
For good probability predictions, you should use post-hoc calibration. With @Eugene_Berta, Michael Jordan, and @BachFrancis we argue that early stopping and tuning should account for this! Using the loss after post-hoc calibration often avoids premature stopping. 🧵1/
5
1
21
7,533
Characterizing finely the decay of eigenvalues of kernel matrices: many people need it, but explicit references are hard to find. This blog post reviews amazing asymptotic results from Harold Widom (1963!) and proposes new non-asymptotic bounds. francisbach.com/spectrum-ker…
1
23
1
126
10,001
A free book: Learning Theory from First Principles by @BachFrancis It covers a bunch of key topics from machine learning (ML) theory and practice, such as: - Math basics - Supervised learning - Generalization, overfitting & adaptivity - Tools to design learning algorithms - Optimization in ML - Local, Kernel and sparse methods - Neural networks - Ensembles - Online learning - Overparameterized models and more! The book also includes simple experiments (in MATLAB and Python), exercises, and references to more advanced material Read it here: di.ens.fr/~fbach/ltfp_book.p…
2
100
2
518
33,871
Michael Jordan is indeed one of the greatest thinkers in the history of AI 🐐 Economics, incentives (mechanism design), information flow, creativity, cooperation, greed and power struggles are important topics that we crucially need to understand better for the benefit of humanity and all intelligent beings. The worst that could happen is that kind, empathetic, empowering, cooperative, helpful AIs are never realised or don’t become ubiquitous in our lives. Thanks @BachFrancis for sharing.
Francis Bach@BachFrancis7 Feb 2025
An inspirational talk by Michael Jordan: a refreshing, deep, and forward-looking vision for AI beyond LLMs. youtube.com/live/W0QLq4qEmKg…
2
12
74
15,197
Sierra Team retweeted
Inria@Inria6 Feb 2025
[🔴#IAScienceSociety] @BachFrancis (@inria_paris-@ENS_ParisSaclay) participe au symposium "The Mathematics of #MachineLearning" aux côtés de @gabrielpeyre, Gilles Louppe (@UniversiteLiege), Gersende Fort (@CNRS) et Vianney Perchet (@INSAE @IP_Paris_).
8
1
25
7,691
Sierra Team retweeted
Inria@Inria6 Feb 2025
🔴 @Inria est présent à la conférence "AI,Science and society" à @IP_Paris_, prélude au #SommetActionIA et sous la direction du Pr. Michael Jordan (@UCBerkeley-@Inria) ! L'événement a été inauguré ce matin par Michael Jordan et cet après-midi par @ClaraChappaz 🗣
9
1
16
2,253
My book is (at last) out, just in time for Christmas! A blog post to celebrate and present it: francisbach.com/my-book-is-o…
32
306
18
1,909
235,935
Bravo Bertille et Marc!
Centre Inria de Paris@inria_paris2 Dec 2024
Replying to @inria_paris @MissBrutus @InriaParisNLP @CNRSinformatics @ENS_ULM
🎓#PhDs | Félicitations à @BertilleFollain et Marc Lambert de l’équipe-projet commune @Sierra_ML_Lab (@CNRSinformatics, @ENS_ULM) et à Roman Gambelin de l'équipe-projet commune DYOGENE (@CNRSinformatics, @ENS_ULM) qui ont soutenu leur #thèse en novembre 🎉👏 !
8
214
🎓#PhDs | Félicitations à Juliette Murris et Alice Rogier de l’équipe @TeamHeka (@univ_paris_cite, @CRCordeliers, @Inserm) ainsi qu'à @oumaymabounou et Céline Moucer des équipes WILLOW et @Sierra_ML_Lab (@CNRSinformatics, @ENS_ULM) qui ont soutenu leur #thèse en octobre 🎉👏 !
1
11
680
#ERCStG 🏆 | Félicitations à @TaylorAdrien, chargé de recherche @inria au centre @inria_paris, membre de l'équipe-projet commune @Sierra_ML_Lab (@CNRS @CNRSinformatics @ENS_ULM), lauréat d'une ERC Starting Grant 👏 Découvrez son portrait et son projet 👉 buff.ly/3YlTBU6
6
2
35
4,979
How fast is gradient descent, *for real*? Some (partial) answers in this new blog post on scaling laws for optimization. francisbach.com/scaling-laws…
3
81
3
465
64,979
Bravo Adrien!
Centre Inria de Paris@inria_paris5 Sep 2024
📰 #Article | Découvrez le projet CASPER, porté par @TaylorAdrien, chercheur au sein de l'équipe-projet commune @Sierra_ML_Lab (@inria_paris /@ENS_ULM/@CNRSinformatics), qui vient d’obtenir une bourse #ERCStG. Félicitations Adrien 🙌 ! 👉 inria.fr/fr/vers-des-algorit… [🧵...]
Portrait d'Adrien Taylor.

ALT Portrait d'Adrien Taylor.

1
26
3,536
Load more