On the schatten norm for matrix based subspace learning and classification

Qianqian Wang; Fang Chen; Quanxue Gao; Xinbo Gao; Feiping Nie

doi:10.1016/j.neucom.2016.07.038

On the schatten norm for matrix based subspace learning and classification

Qianqian Wang
, Fang Chen
, Quanxue Gao
, Xinbo Gao
, Feiping Nie

科研成果: 期刊稿件 › 文章 › 同行评审

22 引用（Scopus）

摘要

Schatten norm, especially nuclear norm (p=1) has been widely used as an approximation of matrix rank and regularized term in the criterion function in pattern recognition and machine learning. In this paper, we point out that Schatten norm (p≤1) is also an effective and robust distance metric in the classification stage and can help improve the classification accuracy of matrix based feature extraction methods. Extensive experiments illustrate the effectiveness of Schatten norm (p≤1).

源语言	英语
页（从-至）	192-199
页数	8
期刊	Neurocomputing
卷	216
DOI	https://doi.org/10.1016/j.neucom.2016.07.038
出版状态	已出版 - 5 12月 2016
已对外发布	是

访问文件

10.1016/j.neucom.2016.07.038

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{8e2736935ace404ab2b7fd2719b10dc4,

title = "On the schatten norm for matrix based subspace learning and classification",

abstract = "Schatten norm, especially nuclear norm (p=1) has been widely used as an approximation of matrix rank and regularized term in the criterion function in pattern recognition and machine learning. In this paper, we point out that Schatten norm (p≤1) is also an effective and robust distance metric in the classification stage and can help improve the classification accuracy of matrix based feature extraction methods. Extensive experiments illustrate the effectiveness of Schatten norm (p≤1).",

keywords = "Dimensionality reduction, Nuclear norm, Two-dimensional subspace methods",

author = "Qianqian Wang and Fang Chen and Quanxue Gao and Xinbo Gao and Feiping Nie",

note = "Publisher Copyright: {\textcopyright} 2016 Elsevier B.V.",

year = "2016",

month = dec,

day = "5",

doi = "10.1016/j.neucom.2016.07.038",

language = "英语",

volume = "216",

pages = "192--199",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - On the schatten norm for matrix based subspace learning and classification

AU - Wang, Qianqian

AU - Chen, Fang

AU - Gao, Quanxue

AU - Gao, Xinbo

AU - Nie, Feiping

PY - 2016/12/5

Y1 - 2016/12/5

N2 - Schatten norm, especially nuclear norm (p=1) has been widely used as an approximation of matrix rank and regularized term in the criterion function in pattern recognition and machine learning. In this paper, we point out that Schatten norm (p≤1) is also an effective and robust distance metric in the classification stage and can help improve the classification accuracy of matrix based feature extraction methods. Extensive experiments illustrate the effectiveness of Schatten norm (p≤1).

AB - Schatten norm, especially nuclear norm (p=1) has been widely used as an approximation of matrix rank and regularized term in the criterion function in pattern recognition and machine learning. In this paper, we point out that Schatten norm (p≤1) is also an effective and robust distance metric in the classification stage and can help improve the classification accuracy of matrix based feature extraction methods. Extensive experiments illustrate the effectiveness of Schatten norm (p≤1).

KW - Dimensionality reduction

KW - Nuclear norm

KW - Two-dimensional subspace methods

UR - https://www.scopus.com/pages/publications/84982152983

U2 - 10.1016/j.neucom.2016.07.038

DO - 10.1016/j.neucom.2016.07.038

M3 - 文章

AN - SCOPUS:84982152983

SN - 0925-2312

VL - 216

SP - 192

EP - 199

JO - Neurocomputing

JF - Neurocomputing

ER -

On the schatten norm for matrix based subspace learning and classification

摘要

访问文件

其它文件与链接

指纹

引用此