Variational limits of k-NN graph based functionals on data clouds
share
We consider i.i.d. samples x_1, ..., x_n from a measure ν with density supported on a bounded Euclidean domain D ⊆ R^d where d≥3. A graph on the point cloud is obtained by connecting two points if one of them is among the k-nearest neighbors of the other. Our goal is to study consistency of graph based procedures to clustering, classification and dimensionality reduction by studying the variational convergence of the graph total variation associated to such k-NN graph. We prove that provided k:=k_n scales like n ≫ k_n ≫(n), then the Γ-convergence of the graph total variation towards an appropriate weighted total variation is guaranteed.
READ FULL TEXT