A self-stabilized minor subspace rule

Scott C. Douglas, S. Y. Kung, Shun Ichi Amari

Research output: Contribution to journalArticlepeer-review

101 Scopus citations


In this letter, we present a minor subspace rule that extracts the subspace that spans the m minor components of a n-dimensional vector stationary random process, m < n. The algorithm is self-stabilizing such that the subspace vectors do not need to be periodically normalized to unit modulus, and the algorithm does not require matrix inversions or divides to maintain its stable behavior.

Original languageEnglish (US)
Pages (from-to)328-330
Number of pages3
JournalIEEE Signal Processing Letters
Issue number12
StatePublished - 1998

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics


  • Adaptive algorithm
  • Minor component analysis
  • Subspace methods


Dive into the research topics of 'A self-stabilized minor subspace rule'. Together they form a unique fingerprint.

Cite this