Rounding-based Moves for Metric Labeling

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download
Contributor : M. Pawan Kumar <>
Submitted on : Tuesday, September 30, 2014 - 10:57:46 AM
Last modification on : Thursday, February 7, 2019 - 5:29:16 PM
Long-term archiving on : Wednesday, December 31, 2014 - 10:35:47 AM


Files produced by the author(s)


  • HAL Id : hal-01069910, version 1



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



Record views


Files downloads