English

Feature selection in weakly coherent matrices

Machine Learning 2018-04-05 v1 Machine Learning

Abstract

A problem of paramount importance in both pure (Restricted Invertibility problem) and applied mathematics (Feature extraction) is the one of selecting a submatrix of a given matrix, such that this submatrix has its smallest singular value above a specified level. Such problems can be addressed using perturbation analysis. In this paper, we propose a perturbation bound for the smallest singular value of a given matrix after appending a column, under the assumption that its initial coherence is not large, and we use this bound to derive a fast algorithm for feature extraction.

Keywords

Cite

@article{arxiv.1804.01119,
  title  = {Feature selection in weakly coherent matrices},
  author = {Stephane Chretien and Zhen-Wai Olivier Ho},
  journal= {arXiv preprint arXiv:1804.01119},
  year   = {2018}
}

Comments

14 pages, 6 Figures, Accepted for LVA-ICA 2018 Surrey

R2 v1 2026-06-23T01:13:02.922Z