On Convergence of the Method of Relaxations, an Application to Learning on a Graph. - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2006

On Convergence of the Method of Relaxations, an Application to Learning on a Graph.

Résumé

We present a semi-supervised algorithm to learn an interpolating function with minimal Laplacian semi-norm on a graph. This algorithm is directly inspired by the classical 'method of relaxations' used in physics to get discrete approximate solutions to the Dirichlet problem. We argue that this method is actually a gradient descent minimizing the energy of an interpolating function on the graph. Besides it converges linearly in the number of steps, with a convergence constant bounded with respect to simple characteristics of the graph. As opposed to inversion-based kernel methods on graph, this algorithm can be efficiently implemented to deal with large, complex graphs.
Fichier principal
Vignette du fichier
RelaxOGraph_MLG06_classChg (2).pdf (400.08 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02920470 , version 1 (24-08-2020)

Identifiants

  • HAL Id : hal-02920470 , version 1

Citer

Sylvain Marié, Mark Herbster. On Convergence of the Method of Relaxations, an Application to Learning on a Graph.. 2006. ⟨hal-02920470⟩
23 Consultations
6 Téléchargements

Partager

Gmail Facebook X LinkedIn More