Sierra Team

64 posts

Sierra Team

Sierra Team

@Sierra_ML_Lab

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

Paris Katılım Mart 2021
36 Takip Edilen447 Takipçiler
Sabitlenmiş Tweet
Sierra Team
Sierra Team@Sierra_ML_Lab·
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
Sierra Team tweet media
English
2
9
99
0
Sierra Team retweetledi
Fabian Schaipp
Fabian Schaipp@FSchaipp·
What are good optimizers for diffusion models? 🍂 TLDR: Muon and SOAP are very good. Paper: arxiv.org/pdf/2510.19376
Fabian Schaipp tweet mediaFabian Schaipp tweet media
English
7
45
330
21.3K
Sierra Team retweetledi
Etienne Gauthier
Etienne Gauthier@Gauthier_E_·
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@Googleorg

🎉 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

English
9
9
126
17.3K
Sierra Team retweetledi
Francis Bach
Francis Bach@BachFrancis·
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-t…
GIF
English
4
48
464
29.1K
Sierra Team retweetledi
Francis Bach
Francis Bach@BachFrancis·
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/
GIF
English
2
36
269
19.5K
Sierra Team retweetledi
David Holzmüller
David Holzmüller@DHolzmueller·
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/
David Holzmüller tweet media
English
2
21
128
12.9K
Sierra Team retweetledi
Eugène Berta
Eugène Berta@Eugene_Berta·
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@DHolzmueller

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/

English
0
5
21
7.3K
Sierra Team retweetledi
Francis Bach
Francis Bach@BachFrancis·
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-kerne…
Francis Bach tweet media
English
1
22
128
9.9K
Sierra Team retweetledi
Ksenia_TuringPost
Ksenia_TuringPost@TheTuringPost·
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_bo…
Ksenia_TuringPost tweet mediaKsenia_TuringPost tweet media
English
2
106
530
33.7K
Sierra Team retweetledi
Nando de Freitas
Nando de Freitas@NandoDF·
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@BachFrancis

An inspirational talk by Michael Jordan: a refreshing, deep, and forward-looking vision for AI beyond LLMs. youtube.com/live/W0QLq4qEm…

English
3
10
77
15.1K
Sierra Team retweetledi
Inria
Inria@Inria·
🔴 @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 🗣
Inria tweet mediaInria tweet mediaInria tweet mediaInria tweet media
Français
0
9
16
2.2K
Sierra Team retweetledi
Francis Bach
Francis Bach@BachFrancis·
How fast is gradient descent, *for real*? Some (partial) answers in this new blog post on scaling laws for optimization. francisbach.com/scaling-laws-o…
GIF
English
3
81
473
64.9K

Keşfet

@Googleorg @BachFrancis @Inria @ENS_ULM @Eugene_Berta @DHolzmueller @inria_paris @gabrielpeyre