Scott Pesme
@skate-the-apple.bsky.social
Postdoc at Inria Grenoble with Julien Mairal.
scottpesme.github.io
scottpesme.github.io
Très agréablement surpris par la qualité et la clarté de la vulgarisation de Stéphane Mallat sur les ondelettes et l’“IA” dans cet épisode de France Culture !
www.radiofrance.fr/francecultur...
www.radiofrance.fr/francecultur...
Stéphane Mallat : la palme d'ondes
La médaille d’or du CNRS 2025 sera remise le 17 décembre à Stéphane Mallat. Depuis la création du prix en 1954, c’est une première pour les mathématiques appliquées, auxquelles il a consacré sa carriè...
www.radiofrance.fr
December 3, 2025 at 6:17 PM
Très agréablement surpris par la qualité et la clarté de la vulgarisation de Stéphane Mallat sur les ondelettes et l’“IA” dans cet épisode de France Culture !
www.radiofrance.fr/francecultur...
www.radiofrance.fr/francecultur...
Reposted by Scott Pesme
The PAISS summer school is back with an incredible line of speakers (and more to come). Spread the word !
May 5, 2025 at 4:34 PM
The PAISS summer school is back with an incredible line of speakers (and more to come). Spread the word !
Come and visit us in Grenoble!
Applications are 📣OPEN📣 for #PAISS2025 THE AI summer school in #Grenoble 1-5 Sept! Speakers so far @yann-lecun.bsky.social @dimadamen.bsky.social @arthurgretton.bsky.social @gabrielpeyre.bsky.social @science4all.org A. Cristia J. Revaud M. Caron J. Carpentier M. Vladimirova ➡️ paiss.inria.fr
April 11, 2025 at 8:58 PM
Come and visit us in Grenoble!
I wish there were a `British' button to language models: optimization --> optimisation, behavior --> behaviour, initialization --> initialisation etc...
January 8, 2025 at 4:30 PM
I wish there were a `British' button to language models: optimization --> optimisation, behavior --> behaviour, initialization --> initialisation etc...
Have you ever encountered similar plots? The training makes no progress, followed by a sharp transition where a new “feature” is learnt. And this occurs with a constant stepsize!
Spoiler: An incremental Romain Gary is hidden at the end of this thread...
arxiv.org/abs/2304.00488
Spoiler: An incremental Romain Gary is hidden at the end of this thread...
arxiv.org/abs/2304.00488
November 19, 2024 at 4:49 PM
Have you ever encountered similar plots? The training makes no progress, followed by a sharp transition where a new “feature” is learnt. And this occurs with a constant stepsize!
Spoiler: An incremental Romain Gary is hidden at the end of this thread...
arxiv.org/abs/2304.00488
Spoiler: An incremental Romain Gary is hidden at the end of this thread...
arxiv.org/abs/2304.00488
A (not at all) short presentation of the paper "(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability" which can be found on arxiv: arxiv.org/abs/2302.08982
November 19, 2024 at 4:23 PM
A (not at all) short presentation of the paper "(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability" which can be found on arxiv: arxiv.org/abs/2302.08982