A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces

Masa Aki Takizawa; Masahiro Yukawa; Cedric Richard

doi:10.1109/ICASSP.2015.7178321

A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces

Masa Aki Takizawa, Masahiro Yukawa, Cedric Richard

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

5 Citations (Scopus)

Abstract

This paper presents a stochastic behavior analysis of a kernel-based stochastic restricted-gradient descent method. The restricted gradient gives a steepest ascent direction within the so-called dictionary subspace. The analysis provides the transient and steady state performance in the mean squared error criterion. It also includes stability conditions in the mean and mean-square sense. The present study is based on the analysis of the kernel normalized least mean square (KNLMS) algorithm initially proposed by Chen et al. Simulation results validate the analysis.

Original language	English
Title of host publication	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2001-2005
Number of pages	5
Volume	2015-August
ISBN (Print)	9781467369978
DOIs	https://doi.org/10.1109/ICASSP.2015.7178321
Publication status	Published - 2015 Aug 4
Event	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 2014 Apr 19 → 2014 Apr 24

Other

Other	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Country/Territory	Australia
City	Brisbane
Period	14/4/19 → 14/4/24

Keywords

kernel adaptive filter
performance analysis
reproducing kernel Hilbert space
the KLMS algorithm

ASJC Scopus subject areas

Signal Processing
Software
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2015.7178321

Cite this

Takizawa, M. A., Yukawa, M., & Richard, C. (2015). A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 2015-August, pp. 2001-2005). [7178321] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2015.7178321

A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces. / Takizawa, Masa Aki; Yukawa, Masahiro; Richard, Cedric.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2015-August Institute of Electrical and Electronics Engineers Inc., 2015. p. 2001-2005 7178321.

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

Takizawa, MA, Yukawa, M & Richard, C 2015, A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 2015-August, 7178321, Institute of Electrical and Electronics Engineers Inc., pp. 2001-2005, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, Brisbane, Australia, 14/4/19. https://doi.org/10.1109/ICASSP.2015.7178321

Takizawa MA, Yukawa M, Richard C. A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2015-August. Institute of Electrical and Electronics Engineers Inc. 2015. p. 2001-2005. 7178321 doi: 10.1109/ICASSP.2015.7178321

@inproceedings{e99e460df40a429381b8d57c1447c391,

title = "A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces",

abstract = "This paper presents a stochastic behavior analysis of a kernel-based stochastic restricted-gradient descent method. The restricted gradient gives a steepest ascent direction within the so-called dictionary subspace. The analysis provides the transient and steady state performance in the mean squared error criterion. It also includes stability conditions in the mean and mean-square sense. The present study is based on the analysis of the kernel normalized least mean square (KNLMS) algorithm initially proposed by Chen et al. Simulation results validate the analysis.",

keywords = "kernel adaptive filter, performance analysis, reproducing kernel Hilbert space, the KLMS algorithm",

author = "Takizawa, {Masa Aki} and Masahiro Yukawa and Cedric Richard",

year = "2015",

month = aug,

day = "4",

doi = "10.1109/ICASSP.2015.7178321",

language = "English",

isbn = "9781467369978",

volume = "2015-August",

pages = "2001--2005",

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

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

note = "40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 ; Conference date: 19-04-2014 Through 24-04-2014",

}

TY - GEN

T1 - A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces

AU - Takizawa, Masa Aki

AU - Yukawa, Masahiro

AU - Richard, Cedric

PY - 2015/8/4

Y1 - 2015/8/4

N2 - This paper presents a stochastic behavior analysis of a kernel-based stochastic restricted-gradient descent method. The restricted gradient gives a steepest ascent direction within the so-called dictionary subspace. The analysis provides the transient and steady state performance in the mean squared error criterion. It also includes stability conditions in the mean and mean-square sense. The present study is based on the analysis of the kernel normalized least mean square (KNLMS) algorithm initially proposed by Chen et al. Simulation results validate the analysis.

AB - This paper presents a stochastic behavior analysis of a kernel-based stochastic restricted-gradient descent method. The restricted gradient gives a steepest ascent direction within the so-called dictionary subspace. The analysis provides the transient and steady state performance in the mean squared error criterion. It also includes stability conditions in the mean and mean-square sense. The present study is based on the analysis of the kernel normalized least mean square (KNLMS) algorithm initially proposed by Chen et al. Simulation results validate the analysis.

KW - kernel adaptive filter

KW - performance analysis

KW - reproducing kernel Hilbert space

KW - the KLMS algorithm

UR - http://www.scopus.com/inward/record.url?scp=84946026233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946026233&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2015.7178321

DO - 10.1109/ICASSP.2015.7178321

M3 - Conference contribution

AN - SCOPUS:84946026233

SN - 9781467369978

VL - 2015-August

SP - 2001

EP - 2005

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

Y2 - 19 April 2014 through 24 April 2014

ER -

A stochastic behavior analysis of stochastic restricted-gradient descent algorithm in reproducing kernel hilbert spaces

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this