Abstract
When faced with the large-scale data set, Kernel principal component analysis (KPCA) is infeasible because of the storage and computational problem. To overcome these disadvantages, an accelerated power method of computing kernel principal components is proposed. First, the accelerated Power iteration is introduced to compute the first eigenvalue and corresponding eigenvector. Then the deflation method is repeatedly applied to achieve other higher order eigenvectors. The space and time complexity of the proposed method is greatly reduced. Experimental results confirm the effectiveness of proposed method.
This work is partially supported by NSF of Henan Educational Committee under contract 2010B520005 and Doctor Fund of Henan University of Technology under contract 2009BS013.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Scholkopf, B., Smola, A.: Learning with Kernels: Support Vector MAchines, Regularization, Optimization and Beyond. MIT Press, Cambridge (2002)
Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic Press, London (1990)
Scholkopf, B., Smola, A., Muller, K.R.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation 10, 1299–1319 (1998)
Zheng, W.M., Zou, C.R., Zhao, L.: An Improved Algorithm for Kernel Principal Components Analysis. Neural Processing Letters 22, 49–56 (2005)
Smola, A., Cristianini, N.: Sparse Greefy Matrix Approximation for Machine Learning. In: International Conference on Machine Learning (2000)
Williams, C., Eeger, S.M.: Using the Nystrom Method to Speed up Kernel Machine. In: Advances in Neural Information Processing Systems (2001)
Kim, K.I., Franz, M.O., Scholkopf, B.: Iterative Kernel Principal Component Analysis. IEEE Trans. Pattern Anal. Mach. Intell. 27(9), 1351–1366 (2005)
Shi, W.Y., Guo, Y.F., An, X.Y.: efficient kernel principal component analysis algorithm for large-scale data set. Journal of Software 20(8), 2153–2159 (2009)
Shi, W.Y., Guo, Y.F., Xue, X.Y.: The power and deflationmethod based Kernel Principal Component Analysis. In: International Conference on Intelligent Computing and Intelligent Systems (2010)
Michael, T.H.: Scientific Computing–An Introductory Survey, 3rd edn. The Johns Hopkins University Press, Baltimore (1996)
David, R.K., Cheney, E.W.: Numerical Analysis:Mathematics of Scientific Computing, 3rd edn. Brooks Cole Press, Pacific Grove (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shi, W., Zhang, W. (2011). The Accelerated Power Method for Kernel Principal Component Analysis. In: Zeng, D. (eds) Applied Informatics and Communication. ICAIC 2011. Communications in Computer and Information Science, vol 225. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23220-6_71
Download citation
DOI: https://doi.org/10.1007/978-3-642-23220-6_71
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23219-0
Online ISBN: 978-3-642-23220-6
eBook Packages: Computer ScienceComputer Science (R0)