Stochastic Optimization of PCA with Capped MSG
Stochastic Optimization of PCA with Capped MSG
复制标题
DOI：
--
复制
发表时间：
2013-07
期刊：
影响因子：
--
通讯作者：
R. Arora;Andrew Cotter;N. Srebro
中科院分区：
文献类型：
--
作者：
R. Arora;Andrew Cotter;N. Srebro
我们将 PCA 作为随机优化问题来研究，并提出了一种新颖的随机近似算法，我们将其称为“矩阵随机梯度”(MSG)，以及一个实用的变体，Capped MSG。我们从理论上和实证上研究了该方法。
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.