onlinePCA-package {onlinePCA}

Online Principal Component Analysis

Description

Online PCA algorithms using perturbation methods (perturbationRpca), secular equations (secularRpca), incremental PCA (incRpca, incRpca.block, incRpca.rc), and stochastic optimization (bsoipca,
ccipca, ghapca, sgapca, snlpca). impute handles missing data with the regression approach of Brand (2002). batchpca performs fast batch (offline) PCA using iterative methods. create.basis, coef2fd, fd2coef respectively create B-spline basis sets for functional data (FD), convert FD to basis coefficients, and convert basis coefficients back to FD. updateMean and updateCovariance update the sample mean and sample covariance.

Author(s)

David Degras <[e-mail]>

References

Brand, M. (2002). Incremental singular value decomposition of uncertain data with missing values. European Conference on Computer Vision (ECCV).
Gu, M. and Eisenstat, S. C. (1994). A stable and efficient algorithm for the rank-one modification of the symmetric eigenproblem. SIAM Journal of Matrix Analysis and Applications.
Hegde et al. (2006) Perturbation-Based Eigenvector Updates for On-Line Principal Components Analysis and Canonical Correlation Analysis. Journal of VLSI Signal Processing.
Oja (1992). Principal components, Minor components, and linear neural networks. Neural Networks.
Sanger (1989). Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Networks.
Mitliagkas et al. (2013). Memory limited, streaming PCA. Advances in Neural Information Processing Systems.
Weng et al. (2003). Candid Covariance-free Incremental Principal Component Analysis. IEEE Trans. Pattern Analysis and Machine Intelligence.