Stochastic Optimization of PCA with Capped MSG

07/05/2013

∙

by   Raman Arora, et al.

∙

0

∙

share

We study PCA as a stochastic optimization problem and propose a novel stochastic approximation algorithm which we refer to as "Matrix Stochastic Gradient" (MSG), as well as a practical variant, Capped MSG. We study the method both theoretically and empirically.