Nonlinear Eigenproblems in Data Analysis - Balanced Graph Cuts and the RatioDCA-Prox
Machine Learning
2014-03-25 v2 Machine Learning
Optimization and Control
Abstract
It has been recently shown that a large class of balanced graph cuts allows for an exact relaxation into a nonlinear eigenproblem. We review briefly some of these results and propose a family of algorithms to compute nonlinear eigenvectors which encompasses previous work as special cases. We provide a detailed analysis of the properties and the convergence behavior of these algorithms and then discuss their application in the area of balanced graph cuts.
Keywords
Cite
@article{arxiv.1312.5192,
title = {Nonlinear Eigenproblems in Data Analysis - Balanced Graph Cuts and the RatioDCA-Prox},
author = {Leonardo Jost and Simon Setzer and Matthias Hein},
journal= {arXiv preprint arXiv:1312.5192},
year = {2014}
}