Robust Multi-Manifold Clustering via Simplex Paths

TL;DR

This paper presents a geometric multi-manifold clustering method using simplex path distances, demonstrating robustness to noise and intersections, with theoretical guarantees and scalable implementation.

Contribution

Introduces a novel simplex path distance metric for multi-manifold clustering with theoretical analysis and a scalable algorithm.

Findings

Method outperforms existing MMC algorithms.

Robust to noise, curvature, and small intersection angles.

Provides theoretical guarantees under random sampling.

Abstract

This article introduces a novel, geometric approach for multi-manifold clustering (MMC), i.e. for clustering a collection of potentially intersecting, d-dimensional manifolds into the individual manifold components. We first compute a locality graph on d-simplices, using the dihedral angle in between adjacent simplices as the graph weights, and then compute infinity path distances in this simplex graph. This procedure gives a metric on simplices which we refer to as the largest angle path distance (LAPD). We analyze the properties of LAPD under random sampling, and prove that with an appropriate denoising procedure, this metric separates the manifold components with high probability. We validate the proposed methodology with extensive numerical experiments on both synthetic and real-world data sets. These experiments demonstrate that the method is robust to noise, curvature, and small intersection angle, and generally out-performs other MMC algorithms. In addition, we provide a highly scalable implementation of the proposed algorithm, which leverages approximation schemes for infinity path distance to achieve quasi-linear computational complexity.