Consistency of Cheeger and Ratio Graph Cuts
This provides theoretical guarantees for clustering algorithms, addressing a foundational problem in machine learning for data analysis.
The paper establishes the consistency of graph-cut-based clustering algorithms, showing that minimizers of Cheeger and ratio cuts converge to continuum cut minimizers as sample size increases, with sharp conditions on connectivity radius scaling.
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 the 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.