Optimal Regularization Parameter Estimation for Regularized Discriminant Analysis
作者： Lin Zhu
DOI: 10.1007/978-3-642-24728-6_11
关键词:
摘要: Regularized linear discriminant analysis (RLDA) is a popular LDA-based method for dimension reduction. Despite its good performance, how to choose the parameter of regularizer efficiently still unanswered, especially multi-class situation. In this paper, we first prove that regularizing LDA equivalent augmenting training set in specific way and thereby propose an efficient model selection criterion based on principle maximum information preservation, extensive experiments usefulness efficiency our method.
springer.com
sci-hub.st 参考文章(6)
Jian Yang, Jing-yu Yang, Why can LDA be performed in PCA transformed space Pattern Recognition. ,vol. 36, pp. 563- 566 ,(2003) , 10.1016/S0031-3203(02)00048-1
H. Li, T. Jiang, K. Zhang, Efficient and robust feature extraction by maximum margin criterion IEEE Transactions on Neural Networks. ,vol. 17, pp. 157- 165 ,(2006) , 10.1109/TNN.2005.860852
P.N. Belhumeur, J.P. Hespanha, D.J. Kriegman, Eigenfaces vs. Fisherfaces: recognition using class specific linear projection IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 19, pp. 711- 720 ,(1997) , 10.1109/34.598228
Dacheng Tao, Xuelong Li, Xindong Wu, Stephen J. Maybank, General Tensor Discriminant Analysis and Gabor Features for Gait Recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 29, pp. 1700- 1715 ,(2007) , 10.1109/TPAMI.2007.1096
Jieping Ye, Tao Li, Tao Xiong, R. Janardan, Using Uncorrelated Discriminant Analysis for Tissue Classification with Gene Expression Data IEEE/ACM Transactions on Computational Biology and Bioinformatics. ,vol. 1, pp. 181- 190 ,(2004) , 10.1109/TCBB.2004.45
Shuiwang Ji, Jieping Ye, Generalized Linear Discriminant Analysis: A Unified Framework and Efficient Model Selection IEEE Transactions on Neural Networks. ,vol. 19, pp. 1768- 1782 ,(2008) , 10.1109/TNN.2008.2002078