Bayesian Independent Component Analysis under Hierarchical Model on Independent Components

研究成果: Conference contribution

抄録

Independent component analysis (ICA) deals with the problem of estimating unknown latent variables (independent components) from observed data. One of the previous studies of ICA assumes a Laplace distribution on independent components. However, this assumption makes it difficult to calculate the posterior distribution of independent components. On the other hand, in the problem of sparse linear regression, several studies have approximately calculated the posterior distribution of parameters by assuming a hierarchical model expressing a Laplace distribution. This paper considers ICA in which a hierarchical model expressing a Laplace distribution is assumed on independent components. For this hierarchical model, we propose a method of calculating the approximate posterior distribution of independent components by using a variational Bayes method. Through some experiments, we show the effectiveness of our proposed method.

元の言語English
ホスト出版物のタイトル2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
出版者Institute of Electrical and Electronics Engineers Inc.
ページ959-962
ページ数4
ISBN(電子版)9789881476852
DOI
出版物ステータスPublished - 2019 3 4
イベント10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
継続期間: 2018 11 122018 11 15

出版物シリーズ

名前2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
United States
Honolulu
期間18/11/1218/11/15

Fingerprint

Independent component analysis
Linear regression
Experiments

ASJC Scopus subject areas

  • Information Systems

これを引用

Asaba, K., Saito, S., Horii, S., & Matsushima, T. (2019). Bayesian Independent Component Analysis under Hierarchical Model on Independent Components. : 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings (pp. 959-962). [8659578] (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/APSIPA.2018.8659578

Bayesian Independent Component Analysis under Hierarchical Model on Independent Components. / Asaba, Kai; Saito, Shota; Horii, Shunsuke; Matsushima, Toshiyasu.

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 959-962 8659578 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).

研究成果: Conference contribution

Asaba, K, Saito, S, Horii, S & Matsushima, T 2019, Bayesian Independent Component Analysis under Hierarchical Model on Independent Components. : 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings., 8659578, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 959-962, 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018, Honolulu, United States, 18/11/12. https://doi.org/10.23919/APSIPA.2018.8659578
Asaba K, Saito S, Horii S, Matsushima T. Bayesian Independent Component Analysis under Hierarchical Model on Independent Components. : 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 959-962. 8659578. (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). https://doi.org/10.23919/APSIPA.2018.8659578
Asaba, Kai ; Saito, Shota ; Horii, Shunsuke ; Matsushima, Toshiyasu. / Bayesian Independent Component Analysis under Hierarchical Model on Independent Components. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 959-962 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).
@inproceedings{ae7ba589597249fd8dc0bd117923e879,
title = "Bayesian Independent Component Analysis under Hierarchical Model on Independent Components",
abstract = "Independent component analysis (ICA) deals with the problem of estimating unknown latent variables (independent components) from observed data. One of the previous studies of ICA assumes a Laplace distribution on independent components. However, this assumption makes it difficult to calculate the posterior distribution of independent components. On the other hand, in the problem of sparse linear regression, several studies have approximately calculated the posterior distribution of parameters by assuming a hierarchical model expressing a Laplace distribution. This paper considers ICA in which a hierarchical model expressing a Laplace distribution is assumed on independent components. For this hierarchical model, we propose a method of calculating the approximate posterior distribution of independent components by using a variational Bayes method. Through some experiments, we show the effectiveness of our proposed method.",
author = "Kai Asaba and Shota Saito and Shunsuke Horii and Toshiyasu Matsushima",
year = "2019",
month = "3",
day = "4",
doi = "10.23919/APSIPA.2018.8659578",
language = "English",
series = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "959--962",
booktitle = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",

}

TY - GEN

T1 - Bayesian Independent Component Analysis under Hierarchical Model on Independent Components

AU - Asaba, Kai

AU - Saito, Shota

AU - Horii, Shunsuke

AU - Matsushima, Toshiyasu

PY - 2019/3/4

Y1 - 2019/3/4

N2 - Independent component analysis (ICA) deals with the problem of estimating unknown latent variables (independent components) from observed data. One of the previous studies of ICA assumes a Laplace distribution on independent components. However, this assumption makes it difficult to calculate the posterior distribution of independent components. On the other hand, in the problem of sparse linear regression, several studies have approximately calculated the posterior distribution of parameters by assuming a hierarchical model expressing a Laplace distribution. This paper considers ICA in which a hierarchical model expressing a Laplace distribution is assumed on independent components. For this hierarchical model, we propose a method of calculating the approximate posterior distribution of independent components by using a variational Bayes method. Through some experiments, we show the effectiveness of our proposed method.

AB - Independent component analysis (ICA) deals with the problem of estimating unknown latent variables (independent components) from observed data. One of the previous studies of ICA assumes a Laplace distribution on independent components. However, this assumption makes it difficult to calculate the posterior distribution of independent components. On the other hand, in the problem of sparse linear regression, several studies have approximately calculated the posterior distribution of parameters by assuming a hierarchical model expressing a Laplace distribution. This paper considers ICA in which a hierarchical model expressing a Laplace distribution is assumed on independent components. For this hierarchical model, we propose a method of calculating the approximate posterior distribution of independent components by using a variational Bayes method. Through some experiments, we show the effectiveness of our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85063425549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063425549&partnerID=8YFLogxK

U2 - 10.23919/APSIPA.2018.8659578

DO - 10.23919/APSIPA.2018.8659578

M3 - Conference contribution

T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

SP - 959

EP - 962

BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -