Orthogonal component analysis: A fast dimensionality reduction algorithm

详细信息    查看全文

• 作者：Tao Zhu^a ; ^{tao144@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Ye Xu^b ; ¹ ; ^{ye@cs.dartmouth.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Furao Shen^a ; ^{frshen@nju.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Jinxi Zhao^a ; ^{jxzhao@nju.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Dimensionality reduction ; Orthogonal component ; Intrinsic dimension estimation ; High-speed component learning
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：12 February 2016
• 年：2016
• 卷：177
• 期：Complete
• 页码：136-146
• 全文大小：855 K

文摘

Most existing dimensionality reduction algorithms have two disadvantages: their computational cost is high and they cannot estimate the intrinsic dimension of the original dataset by themselves. To deal with these problems, in this paper we propose a fast linear dimensionality reduction method named Orthogonal Component Analysis (OCA). While avoiding solving eigenproblem and matrix inverse problem, OCA successfully achieves high-speed orthogonal component extraction. By proposing an adaptive threshold scheme, OCA is able to estimate the dimension of the feature space automatically. Meanwhile, the algorithm is guaranteed to be numerical stable. In the experiments, OCA is compared with several typical dimensionality reduction algorithms. The experimental results demonstrate that as a universal algorithm, OCA is efficient and effective.