Title :
Stochastic optimization for PCA and PLS
Author :
Arora, Rajkumar ; Cotter, A. ; Livescu, Karen ; Srebro, Nathan
Author_Institution :
Toyota Technol. Inst. at Chicago, Chicago, IL, USA
Abstract :
We study PCA, PLS, and CCA as stochastic optimization problems, of optimizing a population objective based on a sample. We suggest several stochastic approximation (SA) methods for PCA and PLS, and investigate their empirical performance.
Keywords :
least squares approximations; optimisation; principal component analysis; stochastic processes; CCA; PCA; PLS; SA; stochastic approximation methods; stochastic optimization problems; Approximation methods; Eigenvalues and eigenfunctions; Equations; Optimization; Principal component analysis; Runtime; Vectors;
Conference_Titel :
Communication, Control, and Computing (Allerton), 2012 50th Annual Allerton Conference on
Conference_Location :
Monticello, IL
Print_ISBN :
978-1-4673-4537-8
DOI :
10.1109/Allerton.2012.6483308
