EM Algorithms for PCA and SPCA

@inproceedings{citeulike:710827, abstract = {I present an expectation-maximization (EM) algorithm for principal component analysis (PCA). The algorithm allows a few eigenvectors and eigenvalues to be extracted from large collections of high dimensional data. It is computationally very efficient in space and time. It also naturally accommodates missing information. I also introduce a new variant of PCA called sensible principal component analysis (SPCA) which defines a proper density model in the data space. Learning for SPCA is also done...}, author = {Roweis, Sam }, booktitle = {Advances in Neural Information Processing Systems}, citeulike-article-id = {710827}, editor = {Jordan, Michael I. and Kearns, Michael J. and Solla, Sara A. }, keywords = {em, pca, svd}, posted-at = {2006-08-08 05:24:02}, priority = {5}, publisher = {The MIT Press}, title = {EM Algorithms for {PCA} and {SPCA}}, url = {http://citeseer.ist.psu.edu/roweis98em.html}, volume = {10}, year = {1998} }

TY - CONF ID - citeulike:710827 L3 - citeulike-article-id:710827 TI - EM Algorithms for {PCA} and {SPCA} T2 - Advances in Neural Information Processing Systems VL - 10 PB - The MIT Press N2 - I present an expectation-maximization (EM) algorithm for principal component analysis (PCA). The algorithm allows a few eigenvectors and eigenvalues to be extracted from large collections of high dimensional data. It is computationally very efficient in space and time. It also naturally accommodates missing information. I also introduce a new variant of PCA called sensible principal component analysis (SPCA) which defines a proper density model in the data space. Learning for SPCA is also done... KW - em KW - pca KW - svd AU - Roweis, Sam A2 - Jordan, Michael A2 - Kearns, Michael A2 - Solla, Sara PY - 1998/// UR - http://citeseer.ist.psu.edu/roweis98em.html ER -