Abstract
Sparse principal component analysis (PCA) aims to find principal components as linear combinations of a subset of the original input variables without sacrificing the fidelity of the classical PCA. Most existing sparse PCA methods produce correlated sparse principal components. We argue that many applications of PCA prefer uncorrelated principal components. However, handling sparsity and uncorrelatedness properties in a sparse PCA method is nontrivial. This article proposes an exactly uncorrelated sparse PCA method named EUSPCA, whose formulation is motivated by original views and motivations of PCA as advocated by Pearson and Hotelling. EUSPCA is a non-smooth constrained non-convex manifold optimization problem. We solve it by combining augmented Lagrangian and non-monotone proximal gradient methods. We observe that EUSPCA produces uncorrelated components and maintains a similar or better level of fidelity based on adjusted total variance through simulated and real data examples. In contrast, existing sparse PCA methods produce significantly correlated components. Supplemental materials for this article are available online.
Supplementary Materials
Online appendix: Online appendix consists of three sections. Appendix A includes proofs of the theorems. In Appendix B, an additional discussion on EUSPCA and related methods is presented. Appendix C provides curves of total adjusted variance versus sparsity on the two real data.
R-package: R-package euspca, available at https://github.com/ohrankwon/euspca, contains the codes for solving EUSPCA with regularization using the mixture of augmented Lagrangian and non-monotone proximal gradient methods.
Acknowledgments
The authors would like to thank the editor, the AE, and two anonymous reviewers for constructive comments, which have improved the quality of the article.
Disclosure Statement
The authors report there are no competing interests to declare.