Francis Bach (@bachfrancis) 's Twitter Profile
Francis Bach

@bachfrancis

Researcher in machine learning

ID: 1395481063

linkhttp://francisbach.com/ calendar_today01-05-2013 20:08:10

339 Tweet

17,17K Followers

85 Following

Centre Inria de Paris (@inria_paris) 's Twitter Profile Photo

🏆 #Distinction | Toutes nos félicitations à Gérard Biau (Centre Inria Sorbonne Université), directeur de #SCAI et spécialiste des dynamiques statistiques dans les algorithmes d'IA, qui a été élu à l’Académie des sciences 👏. sorbonne-universite.fr/presse/gerard-…

🏆 #Distinction | Toutes nos félicitations à <a href="/gerardbiau/">Gérard Biau</a> (Centre <a href="/Inria/">Inria</a> <a href="/Sorbonne_Univ_/">Sorbonne Université</a>), directeur de #SCAI et spécialiste des dynamiques statistiques dans les algorithmes d'IA, qui a été élu à l’<a href="/AcadSciences/">Académie des sciences</a> 👏. 
sorbonne-universite.fr/presse/gerard-…
Fabian Schaipp (@fschaipp) 's Twitter Profile Photo

Learning rate schedules seem mysterious? Turns out that their behaviour can be described with a bound from *convex, nonsmooth* optimization. Short thread on our latest paper 🚇 arxiv.org/abs/2501.18965

Francis Bach (@bachfrancis) 's Twitter Profile Photo

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

An inspirational talk by Michael Jordan: a refreshing, deep, and forward-looking vision for AI beyond LLMs.
youtube.com/live/W0QLq4qEm…
Nando de Freitas (@nandodf) 's Twitter Profile Photo

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

Quentin Berthet - going to #ICLR2025 (@qberthet) 's Twitter Profile Photo

🚨 New paper on regression and classification! Adding to the discussion on using least-squares or cross-entropy, regression or classification formulations of supervised problems! A thread on how to bridge these problems:

🚨 New paper on regression and classification!

Adding to the discussion on using least-squares or cross-entropy, regression or classification formulations of supervised problems!

A thread on how to bridge these problems:
Francis Bach (@bachfrancis) 's Twitter Profile Photo

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…

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…
TuringPost (@theturingpost) 's Twitter Profile Photo

A free book: Learning Theory from First Principles by Francis Bach 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 -

A free book: Learning Theory from First Principles by <a href="/BachFrancis/">Francis Bach</a>

It covers a bunch of key topics from machine learning (ML) theory and practice, such as:

- Math basics
- Supervised learning
- Generalization, overfitting &amp; adaptivity
- Tools to design learning algorithms
-
CNRS Sciences informatiques (@cnrsinformatics) 's Twitter Profile Photo

📣 Vous souhaitez tout comprendre (ou presque) sur l'#IA ? Le livre "Tout comprendre (ou presque) sur l'intelligence artificielle" d'Olivier Cappé et Claire Marc est disponible en ligne dès à présent et en physique à partir du jeudi 10 avril ➡️ cnrseditions.fr/catalogue/soci… 🤝 CNRS Editions

📣 Vous souhaitez tout comprendre (ou presque) sur l'#IA ?
Le livre "Tout comprendre (ou presque) sur l'intelligence artificielle" d'Olivier Cappé et Claire Marc est disponible en ligne dès à présent et en physique à partir du jeudi 10 avril
➡️ cnrseditions.fr/catalogue/soci…
🤝 <a href="/CNRSEd/">CNRS Editions</a>
Lénaïc Chizat (@lenaicchizat) 's Twitter Profile Photo

Announcing : The 2nd International Summer School on Mathematical Aspects of Data Science EPFL, Sept 1–5, 2025 Speakers: Bach (Francis Bach) Bandeira Mallat Montanari (Andrea Montanari) Peyré (Gabriel Peyré) For PhD students & early-career researchers Application deadline: May 15

Antonio Orvieto (@orvieto_antonio) 's Twitter Profile Photo

We have a new SSM theory paper, just accepted to COLT, revisiting recall properties of linear RNNs. It's surprising how much one can delve into, and how beautiful it can become. With (and only thanks to) the amazing Alexandre and Francis Bach arxiv.org/pdf/2502.09287

We have a new SSM theory paper, just accepted to COLT, revisiting recall properties of linear RNNs. 

It's surprising how much one can delve into, and how beautiful it can become.

With (and only thanks to) the amazing Alexandre and <a href="/BachFrancis/">Francis Bach</a> 

arxiv.org/pdf/2502.09287
David Holzmüller (@dholzmueller) 's Twitter Profile Photo

For good probability predictions, you should use post-hoc calibration. With Eugène Berta, Michael Jordan, and Francis Bach we argue that early stopping and tuning should account for this! Using the loss after post-hoc calibration often avoids premature stopping. 🧵1/

For good probability predictions, you should use post-hoc calibration. With <a href="/Eugene_Berta/">Eugène Berta</a>, Michael Jordan, and <a href="/BachFrancis/">Francis Bach</a> we argue that early stopping and tuning should account for this! Using the loss after post-hoc calibration often avoids premature stopping. 🧵1/
Francis Bach (@bachfrancis) 's Twitter Profile Photo

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: di.ens.fr/~fbach/fbach_o…

Etienne Gauthier (@gauthier_e_) 's Twitter Profile Photo

Happy to have our recent papers on conformal prediction with e-values presented at COLT by my advisor Francis Bach! Full details here: 📚arxiv.org/abs/2503.13050 📚arxiv.org/abs/2505.13732 #COLT2025

Happy to have our recent papers on conformal prediction with e-values presented at COLT by my advisor <a href="/BachFrancis/">Francis Bach</a>! 
Full details here: 
📚arxiv.org/abs/2503.13050
📚arxiv.org/abs/2505.13732
#COLT2025