ICML 2022spotlight12 citations

Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering

Peng Wang, Huikang Liu, Anthony Man-Cho So, Laura Balzano

Abstract

The K-subspaces (KSS) method is a generalization of the K-means method for subspace clustering. In this work, we present local convergence analysis and a recovery guarantee for KSS, assuming data are generated by the semi-random union of subspaces model, where $N$ points are randomly sampled from $K \ge 2$ overlapping subspaces. We show that if the initial assignment of the KSS method lies within a neighborhood of a true clustering, it converges at a superlinear rate and finds the correct clustering within $\Theta(\log\log N)$ iterations with high probability. Moreover, we propose a thresholding inner-product based spectral method for initialization and prove that it produces a point in this neighborhood. We also present numerical results of the studied method to support our theoretical developments.

BibTeX
@InProceedings{pmlr-v162-wang22r,
  title = 	 {Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering},
  author =       {Wang, Peng and Liu, Huikang and So, Anthony Man-Cho and Balzano, Laura},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {22884--22918},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/wang22r/wang22r.pdf},
  url = 	 {https://proceedings.mlr.press/v162/wang22r.html},
  abstract = 	 {The K-subspaces (KSS) method is a generalization of the K-means method for subspace clustering. In this work, we present local convergence analysis and a recovery guarantee for KSS, assuming data are generated by the semi-random union of subspaces model, where $N$ points are randomly sampled from $K \ge 2$ overlapping subspaces. We show that if the initial assignment of the KSS method lies within a neighborhood of a true clustering, it converges at a superlinear rate and finds the correct clustering within $\Theta(\log\log N)$ iterations with high probability. Moreover, we propose a thresholding inner-product based spectral method for initialization and prove that it produces a point in this neighborhood. We also present numerical results of the studied method to support our theoretical developments.}
}