Sparse loading noisy PCA using an l 0 penalty

M. O. Ulfarsson; V. Solo

doi:10.1109/ICASSP.2012.6288694

Sparse loading noisy PCA using an l 0 penalty

M. O. Ulfarsson, V. Solo

Faculty of Electrical and Computer Engineering

University of Iceland

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

Abstract

In this paper we present a novel model based sparse principal component analysis method based on the l ₀ penalty. We develop an estimation method based on the generalized EM algorithm and iterative hard thresholding and an associated model selection method based on Bayesian information criterion (BIC). The method is compared to a previous sparse PCA method using both simulated data and DNA microarray data.

Original language	English
Title of host publication	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
Pages	3597-3600
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2012.6288694
Publication status	Published - 2012
Event	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Kyoto, Japan Duration: 25 Mar 2012 → 30 Mar 2012

Publication series

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

Conference

Conference	2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Country/Territory	Japan
City	Kyoto
Period	25/03/12 → 30/03/12

Other keywords

estimation
principal component analysis
sparsity

Access to Document

10.1109/ICASSP.2012.6288694

Cite this

Ulfarsson, M. O., & Solo, V. (2012). Sparse loading noisy PCA using an l 0 penalty. In 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings (pp. 3597-3600). Article 6288694 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2012.6288694

@inproceedings{589d90553c5a48c4b28e9460c93dea44,

title = "Sparse loading noisy PCA using an l 0 penalty",

abstract = "In this paper we present a novel model based sparse principal component analysis method based on the l 0 penalty. We develop an estimation method based on the generalized EM algorithm and iterative hard thresholding and an associated model selection method based on Bayesian information criterion (BIC). The method is compared to a previous sparse PCA method using both simulated data and DNA microarray data.",

keywords = "estimation, principal component analysis, sparsity",

author = "Ulfarsson, \{M. O.\} and V. Solo",

year = "2012",

doi = "10.1109/ICASSP.2012.6288694",

language = "English",

isbn = "9781467300469",

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

pages = "3597--3600",

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",

}

Ulfarsson, MO & Solo, V 2012, Sparse loading noisy PCA using an l 0 penalty. in 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings., 6288694, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 3597-3600, 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012, Kyoto, Japan, 25/03/12. https://doi.org/10.1109/ICASSP.2012.6288694

Sparse loading noisy PCA using an l 0 penalty. / Ulfarsson, M. O.; Solo, V.
2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings. 2012. p. 3597-3600 6288694 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

TY - GEN

T1 - Sparse loading noisy PCA using an l 0 penalty

AU - Ulfarsson, M. O.

AU - Solo, V.

PY - 2012

Y1 - 2012

N2 - In this paper we present a novel model based sparse principal component analysis method based on the l 0 penalty. We develop an estimation method based on the generalized EM algorithm and iterative hard thresholding and an associated model selection method based on Bayesian information criterion (BIC). The method is compared to a previous sparse PCA method using both simulated data and DNA microarray data.

AB - In this paper we present a novel model based sparse principal component analysis method based on the l 0 penalty. We develop an estimation method based on the generalized EM algorithm and iterative hard thresholding and an associated model selection method based on Bayesian information criterion (BIC). The method is compared to a previous sparse PCA method using both simulated data and DNA microarray data.

KW - estimation

KW - principal component analysis

KW - sparsity

UR - https://www.scopus.com/pages/publications/84867599852

U2 - 10.1109/ICASSP.2012.6288694

DO - 10.1109/ICASSP.2012.6288694

M3 - Conference contribution

SN - 9781467300469

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 3597

EP - 3600

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 -

Sparse loading noisy PCA using an l <sub>0</sub> penalty