English
Low complexity regularization of inverse problem - Recovery guarantees
Post-edited
Auteurs : Peyré, Gabriel (Auteur de la Conférence)
CIRM (Editeur )
47N10 - Applications in optimization, convex analysis, mathematical programming, economics
62H35 - Image analysis (statistics)
65D18 - Computer graphics, image analysis, and computational geometry
68U10 - Image processing (computing aspects)
90C31 - Sensitivity, stability, parametric optimization
94A08 - Image processing (compression, reconstruction, etc.)
80M50 - Optimization
CIRM (Editeur )
Résumé :
In this talk, we investigate in a unified way the structural properties of a large class of convex regularizers for linear inverse problems. These penalty functionals are crucial to force the regularized solution to conform to some notion of simplicity/low complexity. Classical priors of this kind includes sparsity, piecewise regularity and low-rank. These are natural assumptions for many applications, ranging from medical imaging to machine learning.
imaging - image processing - sparsity - convex optimization - inverse problem - super-resolution
Codes MSC : imaging - image processing - sparsity - convex optimization - inverse problem - super-resolution
47N10 - Applications in optimization, convex analysis, mathematical programming, economics
62H35 - Image analysis (statistics)
65D18 - Computer graphics, image analysis, and computational geometry
68U10 - Image processing (computing aspects)
90C31 - Sensitivity, stability, parametric optimization
94A08 - Image processing (compression, reconstruction, etc.)
80M50 - Optimization
|
Informations sur la Vidéo
Réalisateur : Hennenfent, GuillaumeLangue : Anglais Date de publication : 04/02/14 Date de captation : 17/12/2013 Sous collection : Research talks arXiv category : Statistics Theory ; Optimization and Control ; Machine Learning Domaine : Analysis and its Applications ; Mathematics in Science & Technology Format : QuickTime (.mov) Durée : 01:13:43 Audience : Researchers Download : https://videos.cirm-math.fr/2013-12-17_Peyre.mp4 
|
Informations sur la Rencontre
Nom de la rencontre : Computational geometry days / Journées de géométrie algorithmiqueOrganisateurs de la rencontre : Cohen-Steiner, David ; Mérigot, Quentin Dates : 16/12/13 - 20/12/13 Année de la rencontre : 2013
Données de citation
DOI : 10.24350/CIRM.V.18448203Citer cette vidéo: Peyré, Gabriel (2013). Low complexity regularization of inverse problem - Recovery guarantees. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.18448203 URI : http://dx.doi.org/10.24350/CIRM.V.18448203 |
Bibliographie
