Presentation 2018-06-13
A supervised dimensionality reduction method using linear combinations of multiple eigenvectors
Akira Imakura, Momo Matsuda, Tetsuya Sakurai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Dimensionality reduction methods that reduce the dimension of original data to a low-dimensional subspace such as LPP and LFDA are widely used for clustering and classifications. These dimensionality reduction methods are formulated by minimization or maximization of a matrix trace and solved as few eigenvectors of the corresponding generalized eigenvalue problem. In this paper, based on the concept of the dimensionality reduction methods, we propose a novel supervised dimensionality reduction method that constructs a low-dimensional subspace with linear combinations of multiple eigenvectors. The proposed method needs to compute multiple eigenvectors; however, one can solve them efficiently by complex moment-based parallel eigensolvers.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) dimensionality reduction methods / supervised learning / linear combination of eigenvectors / complex moment-based eigensolvers
Paper # IBISML2018-6
Date of Issue 2018-06-06 (IBISML)

Conference Information
Committee NC / IBISML / IPSJ-BIO / IPSJ-MPS
Conference Date 2018/6/13(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Okinawa Institute of Science and Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Machine Learning Approach to Biodata Mining, and General
Chair Yutaka Hirata(Chubu Univ.) / Hisashi Kashima(Kyoto Univ.)
Vice Chair Hayaru Shouno(UEC) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Hayaru Shouno(Nagoya Univ.) / Masashi Sugiyama(NAIST) / Koji Tsuda(Nagoya Inst. of Tech.) / (AIST)
Assistant Keiichiro Inagaki(Chubu Univ.) / Takashi Shinozaki(NICT) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Bioinformatics and Genomics / Special Interest Group on Mathematical Modeling and Problem Solving
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A supervised dimensionality reduction method using linear combinations of multiple eigenvectors
Sub Title (in English)
Keyword(1) dimensionality reduction methods
Keyword(2) supervised learning
Keyword(3) linear combination of eigenvectors
Keyword(4) complex moment-based eigensolvers
1st Author's Name Akira Imakura
1st Author's Affiliation University of Tsukuba(Univ. Tsukuba)
2nd Author's Name Momo Matsuda
2nd Author's Affiliation University of Tsukuba(Univ. Tsukuba)
3rd Author's Name Tetsuya Sakurai
3rd Author's Affiliation University of Tsukuba(Univ. Tsukuba)
Date 2018-06-13
Paper # IBISML2018-6
Volume (vol) vol.118
Number (no) IBISML-81
Page pp.pp.39-45(IBISML),
#Pages 7
Date of Issue 2018-06-06 (IBISML)