Score matching and sub-Riemannian bridges | Vidéo | Carmin.tv

00:00:00 / 00:00:00

Score matching and sub-Riemannian bridges

De Erlend Grong

Apparaît dans la collection : Geometric Sciences in Action: from geometric statistics to shape analysis / Les sciences géometriques en action: des statistiques géometriques à l'analyse de forme

We discuss how to simulate bridge processes by conditioning a stochastic process on a manifold whose generator is a hypo-elliptic operator. This operator is, up to a drift-term, the sub-Laplacian of a bracketgenerating sub-Riemannian structure, meaning in particular that it has positive smooth density everywhere. The logarithmic gradient of this density is called the score, and we show that it is needed to describe the generator of the bridge process. We therefore discuss several methods for how we can estimate the score using a neural network, with examples. The results are from a joint work with Stefan Sommer (Copenhagen) and Karen Habermann (Warwick).

Informations sur la vidéo

Date de captation 27/05/2024
Date de publication 21/06/2024
Institut CIRM
Licence CC BY NC ND
Langue Anglais
Audience Chercheurs, Doctorants
Réalisateur(s) Guillaume Hennenfent
Format MP4

Données de citation

DOI 10.24350/CIRM.V.20184903
Citer cette vidéo Grong, Erlend (27/05/2024). Score matching and sub-Riemannian bridges. CIRM. Audiovisual resource. DOI: 10.24350/CIRM.V.20184903
URL https://dx.doi.org/10.24350/CIRM.V.20184903

Domaine(s)

Bibliographie

GRONG, Erlend, HABERMANN, Karen, et SOMMER, Stefan. Score matching for sub-Riemannian bridge sampling. arXiv preprint arXiv:2404.15258, 2024. - https://doi.org/10.48550/arXiv.2404.15258

Codes MSC

Dernières questions liées sur MathOverflow

Pour poser une question, votre compte Carmin.tv doit être connecté à mathoverflow

Poser une question sur MathOverflow

Copyright Carmin.tv 2025

Donner son avis