Multi-Manifold Data Modeling : Foundations and Applications

Mercredi 23 juin 2010 14:00-15:00 - Lerman Gilad - University of Minnesota

Résumé : We present several methods for multi-manifold data modeling,rni.e., modeling data by mixtures of possibly intersecting manifolds.rnWe focus on algorithms for the special case of hybrid linear modeling, that is, where the underlying manifolds are affine or linear subspaces.rnWe emphasize various theoretical results supporting the performance of some of these algorithms, in particular their robustness to noisernand outliers. We demonstrate how such theoretical insights guide us in practical choices. We also present various applications of such algorithms.rnThis is part of various joint works with E. Arias-Castro, S. Atev, G. Chen,rnA. Szlam, Y. Wang, T. Whitehouse and T. Zhang

Lieu : 425 - 113-115

Multi-Manifold Data Modeling : Foundations and Applications  Version PDF
août 2020 :

Rien pour ce mois

juillet 2020 | septembre 2020