An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA

Maboud F. Kaloorazi; Jie Chen; Fei Li; Dan Wu

doi:10.1109/ICSPCC52875.2021.9564568

An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA

Maboud F. Kaloorazi, Jie Chen, Fei Li, Dan Wu

School of Marine Science and Technology

Xi'an Shiyou University

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

2 Scopus citations

Abstract

Low-rank matrix factorization algorithms using the randomized sampling paradigm have recently gained momentum, owing to their computational efficiency, high accuracy, robustness, and efficient parallelization. This paper presents a randomized factorization algorithm tailored for low-rank matrices, called Randomized Partial UTV (RaP-UTV) factorization. RaP-Utvis efficient in arithmetic operations, and can harness the parallel structure of advanced computational platforms. The effectiveness of RaP-Utvis demonstrated through synthetic and real-world data. Applications treated in this work include image reconstruction and robust principal component analysis. The results of RaP-UTV are compared with those of multiple algorithms from the literature.

Original language	English
Title of host publication	Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665429184
DOIs	https://doi.org/10.1109/ICSPCC52875.2021.9564568
State	Published - 17 Aug 2021
Event	2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021 - Xi�an, China Duration: 17 Aug 2021 → 19 Aug 2021

Publication series

Name	Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021

Conference

Conference	2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021
Country/Territory	China
City	Xi�an
Period	17/08/21 → 19/08/21

Keywords

background modeling
dimensionality reduction
image recovery
low-rank matrix factorization
Randomized algorithm
UTV decomposition

Access to Document

10.1109/ICSPCC52875.2021.9564568

Cite this

Kaloorazi, M. F., Chen, J., Li, F., & Wu, D. (2021). An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA. In Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021 (Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSPCC52875.2021.9564568

Kaloorazi, Maboud F. ; Chen, Jie ; Li, Fei et al. / An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA. Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021).

@inproceedings{e0b49112fa6340ce929be9dc4b4b8743,

title = "An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA",

abstract = "Low-rank matrix factorization algorithms using the randomized sampling paradigm have recently gained momentum, owing to their computational efficiency, high accuracy, robustness, and efficient parallelization. This paper presents a randomized factorization algorithm tailored for low-rank matrices, called Randomized Partial UTV (RaP-UTV) factorization. RaP-Utvis efficient in arithmetic operations, and can harness the parallel structure of advanced computational platforms. The effectiveness of RaP-Utvis demonstrated through synthetic and real-world data. Applications treated in this work include image reconstruction and robust principal component analysis. The results of RaP-UTV are compared with those of multiple algorithms from the literature.",

keywords = "background modeling, dimensionality reduction, image recovery, low-rank matrix factorization, Randomized algorithm, UTV decomposition",

author = "Kaloorazi, {Maboud F.} and Jie Chen and Fei Li and Dan Wu",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021 ; Conference date: 17-08-2021 Through 19-08-2021",

year = "2021",

month = aug,

day = "17",

doi = "10.1109/ICSPCC52875.2021.9564568",

language = "英语",

series = "Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021",

}

Kaloorazi, MF, Chen, J, Li, F & Wu, D 2021, An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA. in Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021. Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021, Xi�an, China, 17/08/21. https://doi.org/10.1109/ICSPCC52875.2021.9564568

An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA. / Kaloorazi, Maboud F.; Chen, Jie; Li, Fei et al.
Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021).

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

TY - GEN

T1 - An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA

AU - Kaloorazi, Maboud F.

AU - Chen, Jie

AU - Li, Fei

AU - Wu, Dan

PY - 2021/8/17

Y1 - 2021/8/17

N2 - Low-rank matrix factorization algorithms using the randomized sampling paradigm have recently gained momentum, owing to their computational efficiency, high accuracy, robustness, and efficient parallelization. This paper presents a randomized factorization algorithm tailored for low-rank matrices, called Randomized Partial UTV (RaP-UTV) factorization. RaP-Utvis efficient in arithmetic operations, and can harness the parallel structure of advanced computational platforms. The effectiveness of RaP-Utvis demonstrated through synthetic and real-world data. Applications treated in this work include image reconstruction and robust principal component analysis. The results of RaP-UTV are compared with those of multiple algorithms from the literature.

AB - Low-rank matrix factorization algorithms using the randomized sampling paradigm have recently gained momentum, owing to their computational efficiency, high accuracy, robustness, and efficient parallelization. This paper presents a randomized factorization algorithm tailored for low-rank matrices, called Randomized Partial UTV (RaP-UTV) factorization. RaP-Utvis efficient in arithmetic operations, and can harness the parallel structure of advanced computational platforms. The effectiveness of RaP-Utvis demonstrated through synthetic and real-world data. Applications treated in this work include image reconstruction and robust principal component analysis. The results of RaP-UTV are compared with those of multiple algorithms from the literature.

KW - background modeling

KW - dimensionality reduction

KW - image recovery

KW - low-rank matrix factorization

KW - Randomized algorithm

KW - UTV decomposition

UR - http://www.scopus.com/inward/record.url?scp=85118432421&partnerID=8YFLogxK

U2 - 10.1109/ICSPCC52875.2021.9564568

DO - 10.1109/ICSPCC52875.2021.9564568

M3 - 会议稿件

AN - SCOPUS:85118432421

T3 - Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021

BT - Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021

Y2 - 17 August 2021 through 19 August 2021

ER -

Kaloorazi MF, Chen J, Li F, Wu D. An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA. In Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (Proceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021). doi: 10.1109/ICSPCC52875.2021.9564568

An Efficient Randomized Low-Rank Matrix Factorization with Application to Robust PCA

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this