Variational limits of k-NN graph based functionals on data clouds

Abstract

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. The 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 $n\gg k_n\gg \log (n)$, 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.

References in corpus (7)

• Consistency of spectral clustering
• Asymptotic behavior of ${\ell }_p$-based Laplacian regularization in semi-supervised learning
• Consistency of Cheeger and Ratio Graph Cuts
• Spectral Convergence Rate of Graph Laplacian
• On the Consistency of Graph-based Bayesian Learning and the Scalability of Sampling Algorithms
• The game theoretic p-Laplacian and semi-supervised learning with few labels
• Continuum Limit of Posteriors in Graph Bayesian Inverse Problems

Cited by in corpus (1)

• Large data limit for a phase transition model with the p-Laplacian on point clouds