Rounding-based Moves for Metric Labeling - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Rounding-based Moves for Metric Labeling

Résumé

Metric labeling is a special case of energy minimization for pairwise Markov random fields. The energy function consists of arbitrary unary potentials, and pairwise potentials that are proportional to a given metric distance function over the label set. Popular methods for solving metric labeling include (i) move-making algorithms, which iteratively solve a minimum st-cut problem; and (ii) the linear programming (LP) relaxation based approach. In order to convert the fractional solution of the LP relaxation to an integer solution, several randomized rounding procedures have been developed in the literature. We consider a large class of parallel rounding procedures, and design move-making algorithms that closely mimic them. We prove that the multiplicative bound of a move-making algorithm exactly matches the approximation factor of the corresponding rounding procedure for any arbitrary distance function. Our analysis includes all known results for move-making algorithms as special cases.
Fichier principal
Vignette du fichier
K-NIPS2014.pdf (146.27 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01069910 , version 1 (30-09-2014)

Identifiants

  • HAL Id : hal-01069910 , version 1

Citer

M. Pawan Kumar. Rounding-based Moves for Metric Labeling. NIPS - Advances in Neural Information Processing Systems, 2014, Montreal, Canada. ⟨hal-01069910⟩
114 Consultations
107 Téléchargements

Partager

Gmail Facebook X LinkedIn More