Refining Sparse Principal Components
In this paper, we discuss methods to refine locally optimal solutions of sparse PCA. Starting from a local solution obtained by existing algorithms, these methods take advantage of convex relaxations of the sparse PCA problem to propose a refined solution that is still locally optimal but with a higher objective value.
KeywordsConvex Program Convex Relaxation Dominant Eigenvector Sparse Principal Component Analysis Unit Euclidean Sphere
Unable to display preview. Download preview PDF.
Michel Journée is a research fellow of the Belgian National Fund for Scientific Research (FNRS). This paper presents research results of the Belgian Network DYSCO (Dynamical Systems, Control, and Optimization), funded by the Interuniversity Attraction Poles Programme, initiated by the Belgian State, Science Policy Office. The scientific responsibility rests with its authors.
- 1.A. dďAspremont, F. R. Bach, and L. El Ghaoui. Optimal solutions for sparse principal component analysis. Journal of Machine Learning Research, 9:1269– 1294, 2008.Google Scholar
- 4.M. Journ´ee, F. Bach, P.-A. Absil, and R. Sepulchre. Low-rank optimization for semidefinite convex problems. Submitted to SIAM Journal on Optimization (preprint available on ArXiv), 2008.Google Scholar
- 5.M. Journ´ee, Y. Nesterov, P. Richt´arik, and R. Sepulchre. Generalized power method for sparse principal component analysis. Accepted to Journal of Machine Learning Research (preprint available on ArXiv), 2008.Google Scholar
- 8.B. Moghaddam, Y. Weiss, and S. Avidan. Spectral bounds for sparse PCA: Exact and greedy algorithms. In Y. Weiss, B. Schölkopf, and J. Platt, editors, Advances in Neural Information Processing Systems 18, pages 915–922. MIT Press, Cambridge, MA, 2006.Google Scholar