Poster
Stochastic Optimization of PCA with Capped MSG
Raman Arora · Andrew Cotter · Nati Srebro

Fri Dec 6th 07:00 -- 11:59 PM @ Harrah's Special Events Center, 2nd Floor #None

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.

Author Information

Raman Arora (Johns Hopkins University)
Andy Cotter (TTI Chicago)
Nati Srebro (TTI-Chicago)

More from the Same Authors