Issue No. 10 - October (2008 vol. 20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TKDE.2008.57
Shuiwang Ji , Arizona State University, Tempe
Jieping Ye , Arizona State University, Tempe
Linear and kernel discriminant analysis are popular approaches for supervised dimensionality reduction. Uncorrelated and regularized discriminant analysis have been proposed to overcome the singularity problem encountered by classical discriminant analysis. In this paper, we study the properties of kernel uncorrelated and regularized discriminant analysis, called KUDA and KRDA, respectively. In particular, we show that under a mild condition, both linear and kernel uncorrelated discriminant analysis project samples in the same class to a common vector in the dimensionality-reduced space. This implies that uncorrelated discriminant analysis may suffer from the overfitting problem if there are a large number of samples in each class. We show that as the regularization parameter in KRDA tends to zero, KRDA approaches KUDA. This shows that KUDA is a special case of KRDA, and that regularization can be applied to overcome the overfitting problem in uncorrelated discriminant analysis. As the performance of KRDA depends on the value of the regularization parameter, we show that the matrix computations involved in KRDA can be simplified, so that a large number of candidate values can be crossvalidated efficiently. Finally, we conduct experiments to evaluate the proposed theories and algorithms.
Feature extraction or construction, Parameter learning, Singular value decomposition, Eigenvalues and eigenvectors
S. Ji and J. Ye, "Kernel Uncorrelated and Regularized Discriminant Analysis: A Theoretical and Computational Study," in IEEE Transactions on Knowledge & Data Engineering, vol. 20, no. , pp. 1311-1321, 2008.