Francis Bach

Researcher in machine learning

[Francis Bach @BachFrancis]

@JulyanArbel Avec Grenoble en tête!

[Francis Bach @BachFrancis]

L’Inria et le CNRS toujours au top, cette fois-ci avec nos amis de Grenoble. 170km, 5200m de dénivelé positif pour une Etape du Tour autour de l’Alpe d’Huez. Bravo à @julienmairal, @olivier_cappe et @JulyanArbel.

[Sacha Braun @PotoSacho]

Want to directly minimize the conditional quantile of your predictions?🔥

With Michael I. Jordan & @BachFrancis we introduce SLS regression. We use volume as a direct optimization criterion for estimating conditional HDRs.

Plus: it’s conformal-ready.
📝https://t.co/hdgIRdbG53

[Elliot Paquette @poseypaquet]

The High-Dimensional Learning Dynamics Workshop @ ICML 2026 🇰🇷, with a special focus on scaling laws, is coming up, July 10!
Submission Deadline: May 11 AoE (extended).

@Locchiu @albertobietti @JustinLin610 @inbarser @BachFrancis @ShamKakade6 @andrewgwils @blake__bordelon @_brloureiro @Qiuzihanhan

[Francis Bach @BachFrancis]

Great! Time to sharpen our pencils for some great submissions to present in Paris.

[NeurIPS Europe @EurIPSConf]

Today NeurIPS is announcing our official satellite event in Paris.

After responding to the call from Ellis following the success of EurIPS in December, we are pleased to reach a new milestone by joining forces with the NeurIPS organizing committee for the 2026 edition!

[NeurIPS Europe @EurIPSConf]

Today NeurIPS is announcing our official satellite event in Paris.

After responding to the call from Ellis following the success of EurIPS in December, we are pleased to reach a new milestone by joining forces with the NeurIPS organizing committee for the 2026 edition!

[Francis Bach @BachFrancis]

Looking for alternatives to quadratic functions for closed-form analysis in optimization? This post explores matrix Riccati dynamics and their applications to neural networks. https://t.co/nEJdNGnNEW

[Edgar Dobriban @EdgarDobriban]

We are excited to announce the workshop *Theory and Applications of Calibration for Modern AI* held at AISTATS (May 5, 2026; Tangier, Morocco)!

This workshop aims to bring together researchers and practitioners interested in the calibration of machine learning and AI models from a variety of areas; encompassing theory, methods, and applications.

Calibration has always been an important topic at the interface of many different areas. Despite this, there is no well-established "home" for discussion about calibration. We aim to fill this gap.

We are thrilled to have a great lineup of speakers, including Peter Flach (delivering a tutorial), Ewout W. Steyerberg, Johanna Ziegel, @nhaghtal, Futoshi Futami, and @BuettnerFlo.

We also accept submissions for workshop papers, which will be presented at our poster session. Deadline: *February 20, 2026*. (Openreview link below.)

Please find more details on our website: https://t.co/SuakcagchV.

Spread the word and submit your work! Glad to co-organize with @Eugene_Berta, @SebGGruber, @TPopordanoska, @yifanwu2014 and @BachFrancis.

[Sacha Braun @PotoSacho]

📢 How can you measure conditional miscoverage ??

With @DHolzmueller, Michael I. Jordan & @BachFrancis, we recast conditional coverage as classification, offering a new lens on both its meaning and its measurement. (+ release a package to compute our metric in 2 lines of code)!

[Francis Bach @BachFrancis]

Together with the great Frederik Kunstner (https://t.co/PP2JY3QqK4)

[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: https://t.co/uoy5GPrZek

[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: https://t.co/uoy5GPrZek

[Sacha Braun @PotoSacho]

📢 New paper on arXiv alert!

With @Eugene_Berta, Michael I. Jordan & @BachFrancis we improve conditional coverage in conformal prediction + handle missing outputs + other extensions you should definitely check in the paper !🎯 #conformalPrediction

[Francis Bach @BachFrancis]

Avec en prime une photo du lac de Roselend.

[Francis Bach @BachFrancis]

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_cappe! #LEtapeduTour

[Francis Bach @BachFrancis]

Tired of lengthy computations to derive scaling laws? This post is made for you: discover the sharpness of the z-transform!
https://t.co/k1CJu0CVoR

[Francis Bach @BachFrancis]

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.
https://t.co/HUJh97pq5N

[Etienne Gauthier @Gauthier_E_]

Happy to have our recent papers on conformal prediction with e-values presented at COLT by my advisor @BachFrancis!
Full details here:
📚https://t.co/exKCl7g5Pf
📚https://t.co/YFtmxeVTtN
#COLT2025

[Francis Bach @BachFrancis]

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: https://t.co/cLjuUPksXA

[Francis Bach @BachFrancis]

Take a break from the heat and check it out!

[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