Archives
Chargement de la vue.
Séminaire des jeunes
Bâtiment Fermat, salle 4205EDP : Annabelle Collin (Université de Nantes) : Sequential Data Assimilation for Oncology: Theory & Practice illustrations.
Bâtiment Fermat, salle 4205Abstract: The development of PDE models capable of describing tumor growth may help to monitor disease progression or predict the efficacy of different therapeutic strategies. However, to be truly informative or predictive, these models need to be corrected and/or parameterized
EDP : Simão Correia (Instituto Superior Técnico, Lisbonne) : Blow-up stability of self-similar solutions to the modified Korteweg-de Vries equation
Bâtiment Fermat, salle 4205Abstract : Self-similar solutions for the modified Korteweg-de Vries equation are of both physical and mathematical interest. On the physical side, among several applications, they model the formation of sharp corners in planar vortex patches. Mathematically, they describe the asymptotic
PS : Benjamin Dupuis (INRIA et ENS Paris) : Data-dependent Uniform Generalization Bounds
Bâtiment Fermat, salle 4205We study data-dependent uniform generalization bounds by approaching the problem from a PAC-Bayesian perspective. We first apply the PAC-Bayesian framework on ``random sets'' in a rigorous way, where the training algorithm is assumed to output a data-dependent hypothesis set after
PS : Umut Simsekli (INRIA et ENS Paris) : Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
Bâtiment Fermat, salle 4205Neural network compression has been an increasingly important subject, not only due to its practical relevance, but also due to its theoretical implications, as there is an explicit connection between compressibility and generalization error. In this talk, I will present