English

Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph

Machine Learning 2019-07-26 v1 Information Theory math.IT Machine Learning

Abstract

Spectral Method is a commonly used scheme to cluster data points lying close to Union of Subspaces by first constructing a Random Geometry Graph, called Subspace Clustering. This paper establishes a theory to analyze this method. Based on this theory, we demonstrate the efficiency of Subspace Clustering in fairly broad conditions. The insights and analysis techniques developed in this paper might also have implications for other random graph problems. Numerical experiments demonstrate the effectiveness of our theoretical study.

Keywords

Cite

@article{arxiv.1907.10906,
  title  = {Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph},
  author = {Gen Li and Yuantao Gu},
  journal= {arXiv preprint arXiv:1907.10906},
  year   = {2019}
}

Comments

22 pages, 5 figures