Journal
SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE
Volume 1, Issue 1, Pages 93-120Publisher
SIAM PUBLICATIONS
DOI: 10.1137/18M1188999
Keywords
k-NN graph; discrete to continuum limit; Gamma-convergence; spectral clustering; Cheeger cut; graph cut
Categories
Ask authors/readers for more resources
This paper studies the large sample asymptotics of data analysis procedures based on the optimization of functionals defined on k-NN graphs on point clouds. This paper is framed in the context of minimization of balanced cut functionals, but our techniques, ideas, and results can be adapted to other functionals of relevance. We rigorously show that provided the number of neighbors in the graph k := k(n) scales with the number of points in the cloud as n >> k(n) >> log(n), then with probability one the solution to the graph cut optimization problem converges towards the solution of an analogue variational problem at the continuum level.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available