Différences
Ci-dessous, les différences entre deux révisions de la page.
Les deux révisions précédentes Révision précédente Prochaine révision | Révision précédente | ||
start [2025/05/13 17:50] Djalil Chafaï |
start [2025/06/28 21:42] (Version actuelle) Djalil Chafaï |
||
---|---|---|---|
Ligne 6: | Ligne 6: | ||
/* **Image.** Portrait de phase du polynôme caractéristique réciproque d'une matrice gaussienne de grande dimension ([[https:// | /* **Image.** Portrait de phase du polynôme caractéristique réciproque d'une matrice gaussienne de grande dimension ([[https:// | ||
- | * **Concept[[gt|.]]** Exposés de probas accessibles, | + | * **Concept[[gt|.]]** Exposés de probas accessibles, |
* **Audience.** Amateurs de probas à l' | * **Audience.** Amateurs de probas à l' | ||
+ | * **Année 2025-2026.** | ||
+ | * **Organisateurs[[organisation|.]]** [[https:// | ||
+ | * **Horaire et lieu.** Un lundi par mois, à 11h, salle W. À l' | ||
+ | * **Programme.** | ||
+ | * 29 septembre 2025. **[[https:// | ||
+ | * 13 octobre 2025. **[[https:// | ||
+ | * 17 novembre 2025. **[[https:// | ||
+ | * 15 décembre 2025. **[[https:// | ||
+ | * 12 janvier 2026. [[|]]. **Titre à préciser.**\\ //// | ||
+ | * 16 février 2026. [[|]]. **Titre à préciser.**\\ //// | ||
+ | * 16 mars 2026. [[|]]. **Titre à préciser.**\\ //// | ||
+ | * 13 avril 2026. [[|]]. **Titre à préciser.**\\ //// | ||
+ | * 11 mai 2026. [[|]]. **Titre à préciser.**\\ //// | ||
* **Année 2024-2025.** | * **Année 2024-2025.** | ||
* **Organisateurs[[organisation|.]]** [[https:// | * **Organisateurs[[organisation|.]]** [[https:// | ||
Ligne 24: | Ligne 37: | ||
In this talk, I will present a connection between these three distinct problems. By focusing on the asymptotic regime of high data dimensionality and large sample sizes, I will show how analytical techniques and theoretical insights from the REM can be leveraged to study both KDE and diffusion models. In particular, I will highlight how phase transitions observed in the REM, and their connection to extreme value theory and limiting laws of sums of i.i.d. random variables, have remarkable counterparts and consequences for these other problems in statistics and machine learning.// | In this talk, I will present a connection between these three distinct problems. By focusing on the asymptotic regime of high data dimensionality and large sample sizes, I will show how analytical techniques and theoretical insights from the REM can be leveraged to study both KDE and diffusion models. In particular, I will highlight how phase transitions observed in the REM, and their connection to extreme value theory and limiting laws of sums of i.i.d. random variables, have remarkable counterparts and consequences for these other problems in statistics and machine learning.// | ||
* 12 mai 2025. [[|Gérard Ben Arous (NYU & IHES)]]. **Local geometry of high-dimensional mixture models: Effective spectral theory and dynamical transitions.**\\ //I will survey recent progress in the understanding of the optimization dynamics for high dimensional ML tasks, and in particular the local geometry of empirical risks in high dimensions in the case of classification tasks, via the spectral theory of their Hessian and information matrices. Joint work with Aukosh Jagannath, Jiaoyang Huang, Reza Gheissari.// | * 12 mai 2025. [[|Gérard Ben Arous (NYU & IHES)]]. **Local geometry of high-dimensional mixture models: Effective spectral theory and dynamical transitions.**\\ //I will survey recent progress in the understanding of the optimization dynamics for high dimensional ML tasks, and in particular the local geometry of empirical risks in high dimensions in the case of classification tasks, via the spectral theory of their Hessian and information matrices. Joint work with Aukosh Jagannath, Jiaoyang Huang, Reza Gheissari.// | ||
- | * 2 juin 2025. **[[https:// | + | * 2 juin 2025. **[[https:// |
\\ | \\ | ||