Quentin Berthet
@qberthet.bsky.social
Machine learning
Google DeepMind
Paris
Google DeepMind
Paris
Pinned
Quentin Berthet
@qberthet.bsky.social
· Feb 10
🚨 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:
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:
Reposted by Quentin Berthet
🚨AISTATS workshop proposals open!
Big News: For the first time, there will be a day of workshops at #AISTATS 2026, in Tangier, Morocco 🌴🇲🇦
Quentin Berthet @qberthet.bsky.social and I are workshop chairs.
virtual.aistats.org/Conferences/...
Deadline: Oct 17, AOE
Big News: For the first time, there will be a day of workshops at #AISTATS 2026, in Tangier, Morocco 🌴🇲🇦
Quentin Berthet @qberthet.bsky.social and I are workshop chairs.
virtual.aistats.org/Conferences/...
Deadline: Oct 17, AOE
Call for Workshops
virtual.aistats.org
August 29, 2025 at 1:59 PM
🚨AISTATS workshop proposals open!
Big News: For the first time, there will be a day of workshops at #AISTATS 2026, in Tangier, Morocco 🌴🇲🇦
Quentin Berthet @qberthet.bsky.social and I are workshop chairs.
virtual.aistats.org/Conferences/...
Deadline: Oct 17, AOE
Big News: For the first time, there will be a day of workshops at #AISTATS 2026, in Tangier, Morocco 🌴🇲🇦
Quentin Berthet @qberthet.bsky.social and I are workshop chairs.
virtual.aistats.org/Conferences/...
Deadline: Oct 17, AOE
I will be attending #ICLR2025 in Singapore and #AISTATS2025 in Mai Khao over the next two weeks.
Looking forward to meeting new people and learning about new things. Feel free to reach out if you want to talk about Google DeepMind.
Looking forward to meeting new people and learning about new things. Feel free to reach out if you want to talk about Google DeepMind.
April 17, 2025 at 12:50 PM
I will be attending #ICLR2025 in Singapore and #AISTATS2025 in Mai Khao over the next two weeks.
Looking forward to meeting new people and learning about new things. Feel free to reach out if you want to talk about Google DeepMind.
Looking forward to meeting new people and learning about new things. Feel free to reach out if you want to talk about Google DeepMind.
ICML reviews are out
March 25, 2025 at 9:09 AM
ICML reviews are out
Very proud to have contributed to this work, and very happy to have learnt a lot about votes, choices, and agents!
Looking for a principled evaluation method for ranking of *general* agents or models, i.e. that get evaluated across a myriad of different tasks?
I’m delighted to tell you about our new paper, Soft Condorcet Optimization (SCO) for Ranking of General Agents, to be presented at AAMAS 2025! 🧵 1/N
I’m delighted to tell you about our new paper, Soft Condorcet Optimization (SCO) for Ranking of General Agents, to be presented at AAMAS 2025! 🧵 1/N
February 24, 2025 at 10:37 PM
Very proud to have contributed to this work, and very happy to have learnt a lot about votes, choices, and agents!
Reposted by Quentin Berthet
📣 New preprint 📣
Learning Theory for Kernel Bilevel Optimization
w/ @fareselkhoury.bsky.social E. Pauwels @michael-arbel.bsky.social
We provide generalization error bounds for bilevel optimization problems where the inner objective is minimized over a RKHS.
arxiv.org/abs/2502.08457
Learning Theory for Kernel Bilevel Optimization
w/ @fareselkhoury.bsky.social E. Pauwels @michael-arbel.bsky.social
We provide generalization error bounds for bilevel optimization problems where the inner objective is minimized over a RKHS.
arxiv.org/abs/2502.08457
February 20, 2025 at 1:55 PM
📣 New preprint 📣
Learning Theory for Kernel Bilevel Optimization
w/ @fareselkhoury.bsky.social E. Pauwels @michael-arbel.bsky.social
We provide generalization error bounds for bilevel optimization problems where the inner objective is minimized over a RKHS.
arxiv.org/abs/2502.08457
Learning Theory for Kernel Bilevel Optimization
w/ @fareselkhoury.bsky.social E. Pauwels @michael-arbel.bsky.social
We provide generalization error bounds for bilevel optimization problems where the inner objective is minimized over a RKHS.
arxiv.org/abs/2502.08457
🚨 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:
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:
February 10, 2025 at 12:00 PM
🚨 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:
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:
Reposted by Quentin Berthet
I've got to say, the guy who accidentally became the Director of the FBI does 100% look like the guy who accidentally becomes the Director of the FBI in a mid-2000s comedy about a guy who accidentally becomes the Director of the FBI
February 5, 2025 at 10:12 PM
I've got to say, the guy who accidentally became the Director of the FBI does 100% look like the guy who accidentally becomes the Director of the FBI in a mid-2000s comedy about a guy who accidentally becomes the Director of the FBI
Reposted by Quentin Berthet
🚀 Policy gradient methods like DeepSeek’s GRPO are great for finetuning LLMs via RLHF.
But what happens when we swap autoregressive generation for discrete diffusion, a rising architecture promising faster & more controllable LLMs?
Introducing SEPO !
📑 arxiv.org/pdf/2502.01384
🧵👇
But what happens when we swap autoregressive generation for discrete diffusion, a rising architecture promising faster & more controllable LLMs?
Introducing SEPO !
📑 arxiv.org/pdf/2502.01384
🧵👇
February 4, 2025 at 3:42 PM
🚀 Policy gradient methods like DeepSeek’s GRPO are great for finetuning LLMs via RLHF.
But what happens when we swap autoregressive generation for discrete diffusion, a rising architecture promising faster & more controllable LLMs?
Introducing SEPO !
📑 arxiv.org/pdf/2502.01384
🧵👇
But what happens when we swap autoregressive generation for discrete diffusion, a rising architecture promising faster & more controllable LLMs?
Introducing SEPO !
📑 arxiv.org/pdf/2502.01384
🧵👇
Reposted by Quentin Berthet
Contrapositives are for cowards. Behold.
![Theorem. If $n$ is an integer and $n^2$ is even, then $n$ is itself even.
Proof. Contrapositives are for cowards, so assume $n$ is an integer and $n^2$ is even. Then $n^2=2k$ for some integer $k$, and thus $n^2-2k=0$. Behold:
\[ n = n + (n^2-2k) = n(n+1)-2k. \]
Both $n(n+1)$ and $2k$ are even, so $n$ is even.
QED.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:4wrxafbsjycxbpjo4e42ht6q/bafkreihucnue4bdyzulcrzddytan5ttdx56rg5ci6cn4vhxw5lebnbdzma@jpeg)
January 22, 2025 at 5:58 PM
Contrapositives are for cowards. Behold.
Reposted by Quentin Berthet
Merci @lemonde.fr pour un joli résumé de mes aventures scientifiques et logiciels 📈📠
www.lemonde.fr/sciences/art...
Beaucoup de messages qui me tiennent à cœur : travail d'équipe, logiciel libre, rigueur scientifique
Merci aux collègues et amis qui ont témoigné, je suis ému de lire
www.lemonde.fr/sciences/art...
Beaucoup de messages qui me tiennent à cœur : travail d'équipe, logiciel libre, rigueur scientifique
Merci aux collègues et amis qui ont témoigné, je suis ému de lire
Gaël Varoquaux, vedette de l’intelligence artificielle et défenseur du logiciel libre
L’informaticien et chercheur à l’Inria est l’expert français le plus cité dans les publications scientifiques portant sur l’IA. Avec Scikit-learn, un programme de machine learning dont il est le cocré...
www.lemonde.fr
December 15, 2024 at 5:36 AM
Merci @lemonde.fr pour un joli résumé de mes aventures scientifiques et logiciels 📈📠
www.lemonde.fr/sciences/art...
Beaucoup de messages qui me tiennent à cœur : travail d'équipe, logiciel libre, rigueur scientifique
Merci aux collègues et amis qui ont témoigné, je suis ému de lire
www.lemonde.fr/sciences/art...
Beaucoup de messages qui me tiennent à cœur : travail d'équipe, logiciel libre, rigueur scientifique
Merci aux collègues et amis qui ont témoigné, je suis ému de lire
Reposted by Quentin Berthet
Thrilled to be co-organizing NeurIPS in Paris at @sorbonne-universite.fr next week!
📑 100 papers from NeurIPS 2024. Nearly twice as many as in 2023!
🧑🎓 over 300 registered participants
✅ a local and sustainable alternative to flying to Vancouver.
More info: neuripsinparis.github.io/neurips2024p...
📑 100 papers from NeurIPS 2024. Nearly twice as many as in 2023!
🧑🎓 over 300 registered participants
✅ a local and sustainable alternative to flying to Vancouver.
More info: neuripsinparis.github.io/neurips2024p...
4th and 5th of December Sorbonne Center for Artificial Intelligence (SCAI)
neuripsinparis.github.io
November 27, 2024 at 4:09 PM
Thrilled to be co-organizing NeurIPS in Paris at @sorbonne-universite.fr next week!
📑 100 papers from NeurIPS 2024. Nearly twice as many as in 2023!
🧑🎓 over 300 registered participants
✅ a local and sustainable alternative to flying to Vancouver.
More info: neuripsinparis.github.io/neurips2024p...
📑 100 papers from NeurIPS 2024. Nearly twice as many as in 2023!
🧑🎓 over 300 registered participants
✅ a local and sustainable alternative to flying to Vancouver.
More info: neuripsinparis.github.io/neurips2024p...
Claimed solution for the moving sofa problem?
It looks intense, I hope it's correct
arxiv.org/abs/2411.19826
It looks intense, I hope it's correct
arxiv.org/abs/2411.19826
Optimality of Gerver's Sofa
We resolve the moving sofa problem by showing that Gerver's construction with 18 curve sections attains the maximum area $2.2195\cdots$.
arxiv.org
December 2, 2024 at 12:49 PM
Claimed solution for the moving sofa problem?
It looks intense, I hope it's correct
arxiv.org/abs/2411.19826
It looks intense, I hope it's correct
arxiv.org/abs/2411.19826
AISTATS reviews are out.
November 28, 2024 at 12:22 PM
AISTATS reviews are out.
Reposted by Quentin Berthet
A big thanks to my co-authors Christian Borgelt, @tobiassutter.bsky.social @hildekuehne.bsky.social Oliver Deussen and Stefano Ermon.
Also a shout-out to the authors of the methods we build on: @qberthet.bsky.social @mblondel.bsky.social @marcocuturi.bsky.social @bachfrancis.bsky.social ky.social
Also a shout-out to the authors of the methods we build on: @qberthet.bsky.social @mblondel.bsky.social @marcocuturi.bsky.social @bachfrancis.bsky.social ky.social
November 28, 2024 at 1:49 AM
A big thanks to my co-authors Christian Borgelt, @tobiassutter.bsky.social @hildekuehne.bsky.social Oliver Deussen and Stefano Ermon.
Also a shout-out to the authors of the methods we build on: @qberthet.bsky.social @mblondel.bsky.social @marcocuturi.bsky.social @bachfrancis.bsky.social ky.social
Also a shout-out to the authors of the methods we build on: @qberthet.bsky.social @mblondel.bsky.social @marcocuturi.bsky.social @bachfrancis.bsky.social ky.social
As an AC/SAC for too many conferences right now, I highly recommend people in these roles to gently nudge reviewers who don't reply after author rebuttal.
People can be forgetful, or have busy lives but will often reply / update their scores when reminded to.
People can be forgetful, or have busy lives but will often reply / update their scores when reminded to.
November 27, 2024 at 1:44 PM
As an AC/SAC for too many conferences right now, I highly recommend people in these roles to gently nudge reviewers who don't reply after author rebuttal.
People can be forgetful, or have busy lives but will often reply / update their scores when reminded to.
People can be forgetful, or have busy lives but will often reply / update their scores when reminded to.