Revisiting Decomposable Submodular Function Minimization with Incidence Relations
Machine Learning
2018-09-26 v3 Computer Vision and Pattern Recognition
Discrete Mathematics
Abstract
We introduce a new approach to decomposable submodular function minimization (DSFM) that exploits incidence relations. Incidence relations describe which variables effectively influence the component functions, and when properly utilized, they allow for improving the convergence rates of DSFM solvers. Our main results include the precise parametrization of the DSFM problem based on incidence relations, the development of new scalable alternative projections and parallel coordinate descent methods and an accompanying rigorous analysis of their convergence rates.
Cite
@article{arxiv.1803.03851,
title = {Revisiting Decomposable Submodular Function Minimization with Incidence Relations},
author = {Pan Li and Olgica Milenkovic},
journal= {arXiv preprint arXiv:1803.03851},
year = {2018}
}
Comments
A part of this work will be presented in NIPS2018