Symmetric generalized low rank approximations of matrices

Kohei Inoue; Hara Kenji; Kiichi Urahama

doi:10.1109/ICASSP.2012.6288042

Symmetric generalized low rank approximations of matrices

Kohei Inoue, Hara Kenji, Kiichi Urahama

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

Recently, the generalized low rank approximations of matrices (GLRAM) have been proposed for dimensionality reduction of matrices such as images. However, in GLRAM, it is necessary for users to specify the numbers of rows and columns in low rank matrices. In this paper, we propose a method for determining them semiautomatically by symmetrizing GLRAM. Experimental results show that the proposed method can determine the optimal ranks of matrices while achieving competitive approximation performance.

Original language	English
Title of host publication	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
Pages	949-952
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2012.6288042
Publication status	Published - 2012
Event	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Kyoto, Japan Duration: Mar 25 2012 → Mar 30 2012

Other

Other	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Country/Territory	Japan
City	Kyoto
Period	3/25/12 → 3/30/12

All Science Journal Classification (ASJC) codes

Signal Processing
Software
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2012.6288042

Cite this

Inoue, K , Kenji, H & Urahama, K 2012, Symmetric generalized low rank approximations of matrices. in 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings., 6288042, pp. 949-952, 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012, Kyoto, Japan, 3/25/12. https://doi.org/10.1109/ICASSP.2012.6288042

@inproceedings{eba4300942db4c53a8f8a9fe034f5d75,

title = "Symmetric generalized low rank approximations of matrices",

abstract = "Recently, the generalized low rank approximations of matrices (GLRAM) have been proposed for dimensionality reduction of matrices such as images. However, in GLRAM, it is necessary for users to specify the numbers of rows and columns in low rank matrices. In this paper, we propose a method for determining them semiautomatically by symmetrizing GLRAM. Experimental results show that the proposed method can determine the optimal ranks of matrices while achieving competitive approximation performance.",

author = "Kohei Inoue and Hara Kenji and Kiichi Urahama",

year = "2012",

doi = "10.1109/ICASSP.2012.6288042",

language = "English",

isbn = "9781467300469",

pages = "949--952",

booktitle = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings",

note = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 ; Conference date: 25-03-2012 Through 30-03-2012",

}

TY - GEN

T1 - Symmetric generalized low rank approximations of matrices

AU - Inoue, Kohei

AU - Kenji, Hara

AU - Urahama, Kiichi

PY - 2012

Y1 - 2012

N2 - Recently, the generalized low rank approximations of matrices (GLRAM) have been proposed for dimensionality reduction of matrices such as images. However, in GLRAM, it is necessary for users to specify the numbers of rows and columns in low rank matrices. In this paper, we propose a method for determining them semiautomatically by symmetrizing GLRAM. Experimental results show that the proposed method can determine the optimal ranks of matrices while achieving competitive approximation performance.

AB - Recently, the generalized low rank approximations of matrices (GLRAM) have been proposed for dimensionality reduction of matrices such as images. However, in GLRAM, it is necessary for users to specify the numbers of rows and columns in low rank matrices. In this paper, we propose a method for determining them semiautomatically by symmetrizing GLRAM. Experimental results show that the proposed method can determine the optimal ranks of matrices while achieving competitive approximation performance.

UR - http://www.scopus.com/inward/record.url?scp=84867593804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867593804&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2012.6288042

DO - 10.1109/ICASSP.2012.6288042

M3 - Conference contribution

AN - SCOPUS:84867593804

SN - 9781467300469

SP - 949

EP - 952

BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings

T2 - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012

Y2 - 25 March 2012 through 30 March 2012

ER -

Symmetric generalized low rank approximations of matrices

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this