The trace ratio optimization problem

T. T. Ngo, M. Bellalij, Y. Saad

Research output: Contribution to journalReview articlepeer-review

36 Scopus citations

Abstract

This paper considers the problem of optimizing the ratio Tr[V T AV ]/Tr[V T BV ] over all unitary matrices V with p columns, where A,B are two positive definite matrices. This problem is common in supervised learning techniques. However, because its numerical solution is typically expensive it is often replaced by the simpler optimization problem which consists of optimizing Tr[V T AV ] under the constraint that V T BV = I, the identity matrix. The goal of this paper is to examine this trace ratio optimization problem in detail, to consider different algorithms for solving it, and to illustrate the use of these algorithms for dimensionality reduction.

Original languageEnglish (US)
Pages (from-to)545-569
Number of pages25
JournalSIAM Review
Volume54
Issue number3
DOIs
StatePublished - Sep 3 2012

Keywords

  • Classification
  • Face recognition
  • Linear dimensionality reduction
  • Trace optimization

Fingerprint Dive into the research topics of 'The trace ratio optimization problem'. Together they form a unique fingerprint.

Cite this