Consistency of Cheeger and Ratio Graph Cuts

This paper establishes the consistency of a family of graph-cut-based algorithms for clustering of data clouds. We consider point clouds obtained as samples of a ground-truth measure. We investigate approaches to clustering based on minimizing objective functionals defined on proximity graphs of the given sample. Our focus is on functionals based on graph cuts like the Cheeger and ratio cuts. We show that minimizers of these cuts converge as the sample size increases to a minimizer of a corresponding continuum cut (which partitions the ground truth measure). Moreover, we obtain sharp conditions on how the connectivity radius can be scaled with respect to the number of sample points for the consistency to hold. We provide results for two-way and for multiway cuts. Furthermore we provide numerical experiments that illustrate the results and explore the optimality of scaling in dimension two.


Published in:
Journal Of Machine Learning Research, 17, 181
Year:
2016
Publisher:
Brookline, Microtome Publ
ISSN:
1532-4435
Keywords:
Laboratories:




 Record created 2017-02-17, last modified 2018-09-13


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)