Antoine Collas

Postdoctoral researcher @Inria_Saclay (@InriaMind team) in machine learning.

[Alexandre Gramfort @agramfort]

Have you ever typed import mne in #Python?
Did it help you publish a paper, save hours, or even land your dream job? 💡
Now’s your chance to give back — @mne_news can finally receive 💸 donations to keep the lights on (CIs, forum, etc.) 🙌 https://t.co/bPPOgp2gqT

[Quentin Bertrand @Qu3ntinB]

I am thrilled to announce that our work on the generalization of flow matching has been accepted to NeurIPS as an oral!!

See you in San Diego 😎

[Ambroise Odonnat @AmbroiseOdonnat]

🥳Very happy to see SKADA-Bench accepted at TMLR 2025 @TmlrOrg! This was a huge team effort to design a reproducible open-source Domain Adaptation benchmark with realistic validation.

📜 https://t.co/CQafMGHCtW
🖥️ https://t.co/SdT49DGrzJ
🧵 https://t.co/qCuq4vWmmS

1/2

[Antoine Collas @AntoineCollas]

MNE-Python 1.10 now includes our EEG montage interpolation method from our EUSIPCO 2024 paper 🎉

→ .interpolate_to() works on Epochs, Evoked, ...
→ One line to align signals across caps

📄 Paper: https://t.co/0FHXJ1nW4v
🧠 Demo: https://t.co/hZBYJJy5P3

#EEG #MNEPython #AI

[Yi Ma @YiMaTweets]

Also, many of my students and colleagues working in the field of AI feel that there is an unfair competition between the academia and the industry. I do not think so. While industry focuses on the technology, academia should focus on the methodology. I believe that, methodology-wise, current practice of AI does not have any major secrets and, in fact, it is rather primitive and brute force. That is the reason why it is easily emulated given sufficient resource for reverse engineering. This is another reason why closed-door proprietary practice is doomed to be surpassed.

[Gael Varoquaux 🦋 @GaelVaroquaux]

Merci @lemondefr pour un joli résumé de mes aventures scientifiques et logiciels 📈📠
https://t.co/i8l6iPExCD
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

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

Thanks for the nice workshop ! It was great to be able to share our work, listen to great talks and have many interesting conversations !

[Antoine Collas @AntoineCollas]

Super proud of this work! Domain Adaptation is the way to go for many applications and Skada will democratize it!

[Antoine Collas @AntoineCollas]

Next week, we’ll present our spotlight paper at #NeurIPS2024 on domain adaptation for EEG data. Join us in East Exhibit Hall A-C on Friday at 4:30 PM! Learn how we address shifts in both data and label distributions. Looking forward to your thoughts!

[geomstats @geomstats]

Geomstats first provides common manifolds embedded in vector spaces.

🌐 Symmetric Positive Definite (SPD) matrices, and its many families of Riemannian metrics
🌐 Hyperbolic spaces
🌐 Hyperspheres
🌐 Stiefel manifolds
🌐 Grassmanians

You can also learn your manifold from data!

[geomstats @geomstats]

Geomstats 2.8.0 is out: Discover differential geometry for learning in Python!

🌐 30+ manifolds
🌐 Connections & Riemannian metrics: geodesics, exp & log maps, parallel transport, curvatures
🌐 Lie groups, fiber bundles, quotient spaces, stratified spaces
https://t.co/zHzCKj9gyG

[Denis A. Engemann @dngman]

I am excited! 🎸🚀 Checkout our latest work accepted @NeurIPSConf on Riemannian domain adaptation for #EEG —led by @apmellot & @AntoineCollas — they prepared a very nice #thread 🪡 👇👇🏼👇🏿

[Antoine Collas @AntoineCollas]

🚀I’m beyond excited to share that our paper has been accepted as a Spotlight at #NeurIPS2024! Super proud of the team’s great work! Once again, we make learning across neuroscience datasets easier!

[Ifigeneia Apostolopoulou @ifaposto]

list of #neurips #neurips2024 papers is out:

https://t.co/K3vuYSni2n

enjoy!

[Simo Ryu @cloneofsimo]

99% ML engineer i talked to don't realize gradient is actually defined via inner product. If you have a different definition of inner product (metric), you have different definition of gradient. This will free up your mind.. now preconditioning and layerwise lr tuning makes lot more sense: its actually redefining your notion of distance.

[Ambroise Odonnat @AmbroiseOdonnat]

🤗Officially started Ph.D. with @IevgenRedko, @rtavenar and Laetitia Chapel @Inria @irisa_lab on Transformers & Distribution Shifts

🥳🇨🇦 Also, 2 papers accepted at #NeurIPS2024

📈 *Spotlight* https://t.co/kphqSjHRHG
✋🏾 MaNO https://t.co/pzojhoYA0R

More details soon!

[Quentin Berthet @qberthet]

#NeurIPS2024 decisions are out

[Antoine Collas @AntoineCollas]

Pymanopt 2.2.1 is here!

Highlights include bug fixes, support for SciPy versions >=1.13, and updated documentation. 🎉 Special thanks to new contributors! See: https://t.co/oCbQge5U6j

#Python #Optimization #Manifolds

[Antoine Collas @AntoineCollas]

@RFlamary @hugues_va @PyTorch @mathusmassias @nicolas_courty @CedricCuaz I am curious to see how well you can speed up ml methods that scale poorly in n and/or d with this