2000 character limit reached
Stochastic Optimization of PCA with Capped MSG
Published 5 Jul 2013 in stat.ML and cs.LG | (1307.1674v1)
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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.