Skip to yearly menu bar Skip to main content


Poster

Stochastic Optimization of PCA with Capped MSG

Raman Arora · Andrew Cotter · Nati Srebro

Harrah's Special Events Center, 2nd Floor

Abstract:

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.

Live content is unavailable. Log in and register to view live content