Accès direct au contenu

CMLA

Version anglaise

aide

Accueil > Manifestations > Séminaires du CMLA

Recherche - Valorisation

Séminaire du CMLA : GANs from a statistical point of view

le 24 janvier 2019
12h-13h

Séminaire animé par Maxime Sangnier (UPMC)

maxime_sangnier.jpg

maxime_sangnier.jpg

Generative Adversarial Networks (GANs) are a class of generative algorithms that have been shown to produce state-of-the art samples, especially in the domain of image creation.

The fundamental principle of GANs is to approximate the unknown distribution of a given data set by optimizing an objective function through an adversarial game between a family of generators and a family of discriminators.

In this talk, we illustrate some statistical properties of GANs, focusing on the deep connection between the adversarial principle underlying GANs and the Jensen-Shannon divergence, together with some optimality characteristics of the problem.

We also analyze the role of the discriminator family and study the large sample properties of the estimated distribution.
Type :
Séminaires - conférences
Lieu(x) :
Campus de Cachan
Bâtiment Cournot, salle C410

Conférencier










Inscriptions

Merci de vous inscrire AVANT LE 22 JANVIER 2019 via le sondage et de choisir sandwich ou salade. Merci d'inscrire également vos invités pour que tout le monde trouve à se sustenter...




Recherche d'une actualité

Recherche d'une actualité