Influence Function and Robust Variant of Kernel Canonical Correlation Analysis

Preprint English OPEN
Alam, Md. Ashad; Fukumizu, Kenji; Wang, Yu-Ping; (2017)
  • Subject: Statistics - Machine Learning
    acm: Software_OPERATINGSYSTEMS | ComputingMethodologies_PATTERNRECOGNITION

Many unsupervised kernel methods rely on the estimation of the kernel covariance operator (kernel CO) or kernel cross-covariance operator (kernel CCO). Both kernel CO and kernel CCO are sensitive to contaminated data, even when bounded positive definite kernels are used... View more
  • References (4)

    [17] J. Kim, C. D. Scott, Robust kernel density estimation, Journal of Machine Learning Research 13 (2012) 2529-2565.

    [18] S. Y. Huang, Y. R. Yeh, S. Eguchi, Robust kernel principal component analysis, Neural Computation 21(11) (2009) 3179-3213.

    [48] Y. Tanaka, Sensitivity analysis in principal component analysis: influence on the subspace spanned by principal components, Communications in Statistics-Theory and Methods 17(9) (1988) 3157-3175.

    [49] Y. Tanaka, Influence functions related to eigenvalue problem which appear in multivariate analysis, Communications in Statistics-Theory and Methods 18(11) (1989) 3991-4010.

  • Metrics
    No metrics available
Share - Bookmark