Lightnews — Scholar-powered news

Francis Bach @bachfrancis.bsky.social · 11d

Together with the great Frederik Kunstner (fkunstner.github.io)

fkunstner.github.io

Francis Bach @bachfrancis.bsky.social · 11d

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...

1 12 47

Francis Bach @bachfrancis.bsky.social · Jul 21

Avec en prime une photo du lac de Roselend.

4

Francis Bach @bachfrancis.bsky.social · Jul 21

Jamais deux sans trois. Le département d’informatique de l’ENS toujours en forme. 131 km, 4500m de dénivelé, cette fois-ci avec du Beaufort aux ravitaillements!
Bravo Olivier Cappé! #LEtapeduTour

1 20

Francis Bach @bachfrancis.bsky.social · Jul 18

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/

1 6 26

Francis Bach @bachfrancis.bsky.social · Jul 18

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/

4 19

Francis Bach @bachfrancis.bsky.social · Jul 13

What if AI isn’t about building solo geniuses, but designing social systems?
Michael Jordan advocates blending ML, economics, and uncertainty management to prioritize social welfare over mere prediction.
A must-read rethink.
arxiv.org/abs/2507.062...

A Collectivist, Economic Perspective on AI

Information technology is in the midst of a revolution in which omnipresent data collection and machine learning are impacting the human world as never before. The word "intelligence" is being used as...

arxiv.org

9 37

Francis Bach @bachfrancis.bsky.social · Jul 1

Big thanks to the COLT 2025 organizers for an awesome event in Lyon! Here are the slides from my keynote this morning in case you’re curious about the references I mentioned: www.di.ens.fr/~fbach/fbach...

www.di.ens.fr

2 19

Reposted by Francis Bach

Julyan Arbel @julyanarbel.bsky.social · Jun 9

Register at PAISS 1-5 Sept 2025 @inria_grenoble with very talented speakers this year 🙂
paiss.inria.fr
cc @mvladimirova.bsky.social

1 4 8

Reposted by Francis Bach

Julien Mairal @jmairal.bsky.social · May 5

The PAISS summer school is back with an incredible line of speakers (and more to come). Spread the word !

1 11 23

Reposted by Francis Bach

Académie des sciences @academiesciences.bsky.social · May 6

Épisode 5 de notre série "Les nouveaux visages de l’Académie des sciences" : La statistique, une science en son temps.

Retrouvez la vidéo sur Youtube : www.youtube.com/watch?v=2AhT...

1 5 13

Reposted by Francis Bach

Lénaïc Chizat @lenaicchizat.bsky.social · Apr 14

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!

Mathematical Aspects of Data Science

Graduate Summer School - EPFL - Sept. 1-5, 2025

mathsdata2025.github.io

1 24 45

Reposted by Francis Bach

Académie des sciences @academiesciences.bsky.social · Apr 1

[NOUVELLE SERIE "LES NOUVEAUX VISAGES DE L'ACADEMIE DES SCIENCES]
Episode n°1 : Anne Canteaut : une architecte de la cryptographie moderne
www.youtube.com/watch?v=xyGC...

1 3 9

Reposted by Francis Bach

Gabriel Peyré @gabrielpeyre.bsky.social · Mar 28

Futur best seller!

2 6 37

Francis Bach @bachfrancis.bsky.social · Mar 24

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...

6 48

Francis Bach @bachfrancis.bsky.social · Mar 5

The must-read introduction to PAC-Bayes!

Pierre Alquier @pierrealquier.bsky.social · Mar 5

I already advertised for this document when I posted it on arXiv, and later when it was published.

This week, with the agreement of the publisher, I uploaded the published version on arXiv.

Less typos, more references and additional sections including PAC-Bayes Bernstein.

arxiv.org/abs/2110.11216

6

Reposted by Francis Bach

Académie des sciences @academiesciences.bsky.social · Feb 11

🔬✨ Journée des Femmes et des filles de science✨🔬

À travers leurs parcours inspirants et leurs engagements, les académiciennes, et toutes les femmes et filles de science façonnent la recherche d’aujourd’hui et de demain.

Pour aller plus loin : urls.fr/PK5xg9

urls.fr

3 26 48

Reposted by Francis Bach

Quentin Berthet @qberthet.bsky.social · Feb 10

Check out our paper, with Lawrence Stewart and @bachfrancis.bsky.social

Link: arxiv.org/abs/2502.02996

1/8

Building Bridges between Regression, Clustering, and Classification

Regression, the task of predicting a continuous scalar target y based on some features x is one of the most fundamental tasks in machine learning and statistics. It has been observed and...

arxiv.org

1 2 9

Reposted by Francis Bach

JP Vert @jpvert.bsky.social · Feb 9

If you're curious of what is "behind a term sheet", don't miss this account by the Cathay innovation team who led our recent series A at Bioptimus

medium.com/cathay-innov...

Behind the Term Sheet: Bioptimus’ $41M Series A

The GPT of Biology Raising the Bar of AI-Driven Scientific Research

medium.com

1 6

Francis Bach @bachfrancis.bsky.social · Feb 7

An inspirational talk by Michael Jordan: a refreshing, deep, and forward-looking vision for AI beyond LLMs.
www.youtube.com/live/W0QLq4q...

2 1 27

Reposted by Francis Bach

Fabian Schaipp @fschaipp.bsky.social · Feb 5

Learning rate schedules seem mysterious? Why is the loss going down so fast during cooldown?
Turns out that this behaviour can be described with a bound from *convex, nonsmooth* optimization.

A short thread on our latest paper 🚞

arxiv.org/abs/2501.18965

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training

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 schedul...

arxiv.org

2 6 31

Reposted by Francis Bach

Eugene Berta @eberta.bsky.social · Feb 3

Early stopping on validation loss? This leads to suboptimal calibration and refinement errors—but you can do better!
With @dholzmueller.bsky.social, Michael I. Jordan, and @bachfrancis.bsky.social, we propose a method that integrates with any model and boosts classification performance across tasks.

4 9 18

Reposted by Francis Bach

JP Vert @jpvert.bsky.social · Jan 5

I've been eagerly awaiting this book for years! At last, a standalone and meticulous exposition of the current mathematical principles of machine learning, adorned with beautiful proofs. Well done and thank you,
@bachfrancis.bsky.social . Discover more here: francisbach.com/my-book-is-o...

My book is (at last) out! – Machine Learning Research Blog

francisbach.com

1 16

Francis Bach @bachfrancis.bsky.social · Dec 21

A happy author discovering the first hard copies

3 16 98

Reposted by Francis Bach

Francis Bach @bachfrancis.bsky.social · Dec 21

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...

2 35 140