Chao Gao, Dan Garber, Nathan Srebro, Jialei Wang, Weiran Wang
TL;DR本文研究了规范相关分析的样本复杂度，提出了一种基于随机优化算法的解决方案，使用Shift-and-Invert Power Iterations进行处理的流式算法，从而实现相同的学习准确性和(样本复杂度的水平)。
Abstract
We tightly analyze the sample complexity of CCA, provide a learning algorithm that achieves optimal statistical performance in time linear in the required number of samples (up to log factors), as well as a streaming al