Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Matrix computations (3rd ed.)
The symmetric eigenvalue problem
The symmetric eigenvalue problem
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Local Discriminant Embedding and Its Variants
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Orthogonal Neighborhood Preserving Projections
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Supervised dimensionality reduction via sequential semidefinite programming
Pattern Recognition
Learning a Mahalanobis distance metric for data clustering and classification
Pattern Recognition
Enhanced graph-based dimensionality reduction with repulsion Laplaceans
Pattern Recognition
Trace ratio criterion for feature selection
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
A convex programming approach to the trace quotient problem
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Trace quotient problems revisited
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Hi-index | 0.00 |
This paper considers the problem of optimizing the ratio $\mathrm{Tr}[V^{T}AV]/\mathrm{Tr}[V^{T}BV]$ 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 $\mathrm{Tr}[V^{T}AV]$ 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.