Abstract | ||
---|---|---|
Kernel Principal Component Analysis extends linear PCA from a Euclidean space to any reproducing kernel Hilbert space. Robustness issues for Kernel PCA are studied. The sensitivity of Kernel PCA to individual observations is characterized by calculating the influence function. A robust Kernel PCA method is proposed by incorporating kernels in the Spherical PCA algorithm. Using the scores from Spherical Kernel PCA, a graphical diagnostic is proposed to detect points that are influential for ordinary Kernel PCA. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1016/j.csda.2009.08.018 | Computational Statistics & Data Analysis |
Keywords | Field | DocType |
influential observation,kernel principal,spherical pca algorithm,kernel pca,ordinary kernel pca,component analysis,reproducing kernel hilbert space,robust kernel pca method,linear pca,spherical kernel pca,euclidean space,kernel principal component analysis | Radial basis function kernel,Principal component regression,Kernel embedding of distributions,Kernel Fisher discriminant analysis,Kernel principal component analysis,Polynomial kernel,Statistics,Variable kernel density estimation,Mathematics,Kernel (statistics) | Journal |
Volume | Issue | ISSN |
54 | 12 | Computational Statistics and Data Analysis |
Citations | PageRank | References |
9 | 0.73 | 15 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michiel Debruyne | 1 | 52 | 3.28 |
Mia Hubert | 2 | 433 | 48.10 |
Johan Van Horebeek | 3 | 20 | 3.38 |