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. |
Year | Venue | DocType |
---|---|---|
2013 | neural information processing systems | Conference |
Volume | Citations | PageRank |
abs/1307.1674 | 28 | 1.39 |
References | Authors | |
10 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
R. Arora | 1 | 489 | 35.97 |
Andrew Cotter | 2 | 851 | 78.35 |
Nathan Srebro | 3 | 3892 | 349.42 |
Cotter, Andy | 4 | 28 | 1.39 |
Srebro, Nati | 5 | 28 | 1.39 |