Adaptive algorithm for sparse system identification using projections onto weighted ℓ1 balls

Konstantinos Slavakis; Yannis Kopsinis; Sergios Theodoridis

doi:10.1109/ICASSP.2010.5495872

Adaptive algorithm for sparse system identification using projections onto weighted ℓ₁ balls

Konstantinos Slavakis, Yannis Kopsinis, Sergios Theodoridis

Digital Technology Center

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

33 Scopus citations

Abstract

This paper presents a novel projection-based adaptive algorithm for sparse system identification. Sequentially observed data are used to generate an equivalent number of closed convex sets, namely hyperslabs, which quantify an associated cost criterion. Sparsity is exploited by the introduction of appropriately designed weighted ℓ₁ balls. The algorithm uses only projections onto hyperslabs and weighted ℓ₁ balls, and results into a computational complexity of order O(L) multiplications/additions and O(Llog₂ L) sorting operations, where L is the length of the system to be estimated. Numerical results are also given to validate the proposed method against very recently developed sparse LMS and RLS type of algorithms, which are considered to belong to the same type of algorithmic family.

Original language	English (US)
Title of host publication	2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3742-3745
Number of pages	4
ISBN (Print)	9781424442966
DOIs	https://doi.org/10.1109/ICASSP.2010.5495872
State	Published - 2010
Event	2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Dallas, TX, United States Duration: Mar 14 2010 → Mar 19 2010

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Other

Other	2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
Country/Territory	United States
City	Dallas, TX
Period	3/14/10 → 3/19/10

Keywords

Adaptive filtering
Projections
Sparsity

Access

10.1109/ICASSP.2010.5495872

OpenUrl availability

Full text

Cite this

Slavakis, K., Kopsinis, Y., & Theodoridis, S. (2010). Adaptive algorithm for sparse system identification using projections onto weighted ℓ₁ balls. In 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings (pp. 3742-3745). Article 5495872 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2010.5495872

Adaptive algorithm for sparse system identification using projections onto weighted ℓ₁ balls. / Slavakis, Konstantinos; Kopsinis, Yannis; Theodoridis, Sergios.
2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2010. p. 3742-3745 5495872 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

Slavakis, K, Kopsinis, Y & Theodoridis, S 2010, Adaptive algorithm for sparse system identification using projections onto weighted ℓ₁ balls. in 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings., 5495872, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 3742-3745, 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010, Dallas, TX, United States, 3/14/10. https://doi.org/10.1109/ICASSP.2010.5495872

Slavakis K, Kopsinis Y, Theodoridis S. Adaptive algorithm for sparse system identification using projections onto weighted ℓ₁ balls. In 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2010. p. 3742-3745. 5495872. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2010.5495872

Slavakis, Konstantinos ; Kopsinis, Yannis ; Theodoridis, Sergios. / Adaptive algorithm for sparse system identification using projections onto weighted ℓ₁ balls. 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2010. pp. 3742-3745 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{e0693c7f267f4b329941a969d0e51a06,

title = "Adaptive algorithm for sparse system identification using projections onto weighted ℓ1 balls",

abstract = "This paper presents a novel projection-based adaptive algorithm for sparse system identification. Sequentially observed data are used to generate an equivalent number of closed convex sets, namely hyperslabs, which quantify an associated cost criterion. Sparsity is exploited by the introduction of appropriately designed weighted ℓ1 balls. The algorithm uses only projections onto hyperslabs and weighted ℓ1 balls, and results into a computational complexity of order O(L) multiplications/additions and O(Llog2 L) sorting operations, where L is the length of the system to be estimated. Numerical results are also given to validate the proposed method against very recently developed sparse LMS and RLS type of algorithms, which are considered to belong to the same type of algorithmic family.",

keywords = "Adaptive filtering, Projections, Sparsity",

author = "Konstantinos Slavakis and Yannis Kopsinis and Sergios Theodoridis",

year = "2010",

doi = "10.1109/ICASSP.2010.5495872",

language = "English (US)",

isbn = "9781424442966",

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

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

pages = "3742--3745",

booktitle = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings",

note = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 ; Conference date: 14-03-2010 Through 19-03-2010",

}

TY - GEN

T1 - Adaptive algorithm for sparse system identification using projections onto weighted ℓ1 balls

AU - Slavakis, Konstantinos

AU - Kopsinis, Yannis

AU - Theodoridis, Sergios

PY - 2010

Y1 - 2010

N2 - This paper presents a novel projection-based adaptive algorithm for sparse system identification. Sequentially observed data are used to generate an equivalent number of closed convex sets, namely hyperslabs, which quantify an associated cost criterion. Sparsity is exploited by the introduction of appropriately designed weighted ℓ1 balls. The algorithm uses only projections onto hyperslabs and weighted ℓ1 balls, and results into a computational complexity of order O(L) multiplications/additions and O(Llog2 L) sorting operations, where L is the length of the system to be estimated. Numerical results are also given to validate the proposed method against very recently developed sparse LMS and RLS type of algorithms, which are considered to belong to the same type of algorithmic family.

AB - This paper presents a novel projection-based adaptive algorithm for sparse system identification. Sequentially observed data are used to generate an equivalent number of closed convex sets, namely hyperslabs, which quantify an associated cost criterion. Sparsity is exploited by the introduction of appropriately designed weighted ℓ1 balls. The algorithm uses only projections onto hyperslabs and weighted ℓ1 balls, and results into a computational complexity of order O(L) multiplications/additions and O(Llog2 L) sorting operations, where L is the length of the system to be estimated. Numerical results are also given to validate the proposed method against very recently developed sparse LMS and RLS type of algorithms, which are considered to belong to the same type of algorithmic family.

KW - Adaptive filtering

KW - Projections

KW - Sparsity

UR - http://www.scopus.com/inward/record.url?scp=78049384053&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049384053&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2010.5495872

DO - 10.1109/ICASSP.2010.5495872

M3 - Conference contribution

AN - SCOPUS:78049384053

SN - 9781424442966

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

SP - 3742

EP - 3745

BT - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010

Y2 - 14 March 2010 through 19 March 2010

ER -