arrow
Return

The Trace Ratio Optimization Problem

delete2012-01-01
delete71
PRE
AI
T
Trung Thanh Ngo *
M
M. Bellalij
Y
Yousef Saad
DOI:10.1137/120864799delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
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.
Keywords:
trace optimization
classification
linear dimensionality reduction
face recognition

Journal

SIAM Review cover
SIAM Review
IF:
6.1
Papers:
888
Citations:
1.4W

Organization

U
university of minnesota -twin cities
Scholars:
2
Papers: 1
Citations: 14
Cited Papers

Cited Papers

13C NMR investigation of carbon nanotubes and derivatives
err2001-08-01
err0
PREAI
errC. Goze Bac; P. Bernier; S. Latil; V. Jourdain; A. Rubio; S.H. Jhang; S.W. Lee; Y.W. Park; M. Holzinger; A. Hirsch
errShare
errSave
Supervised dimensionality reduction via sequential semidefinite programming
err2008-12-01
err26
errOAAI
errShen, Chunhua; Li, Hongdong; Brooks, Michael J.
errShare
errSave
Learning a Mahalanobis distance metric for data clustering and classification
err2008-12-01
err503
PREAI
errXiang, Shiming; Nie, Feiping; Zhang, Changshui
errShare
errSave
no more