On adaptivity of online model selection method based on multikernel adaptive filtering

Masahiro Yukawa, Ryu Ichiro Ishii

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We investigate adaptivity of the online model selection method which has been proposed recently within the multikernel adaptive filtering framework. Specifically, we consider a situation in which the nonlinear system under study changes during adaptation and an appropriate kernel also does accordingly. Our time-varying cost functions involve three regularizers: the ℓ1 norm and two block ℓ1 norms which promote sparsity both in the kernel and data groups. The block ℓ1 regularizers are approximated by their Moreau envelopes, and the adaptive proximal forward-backward splitting (APFBS) method is applied to the approximated cost function. Numerical examples show that the proposed algorithm can adaptively estimate a reasonable model.

Original languageEnglish
Title of host publication2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
DOIs
Publication statusPublished - 2013
Event2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 - Kaohsiung, Taiwan, Province of China
Duration: 2013 Oct 292013 Nov 1

Other

Other2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
CountryTaiwan, Province of China
CityKaohsiung
Period13/10/2913/11/1

Fingerprint

Adaptive filtering
Cost functions
Nonlinear systems

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Yukawa, M., & Ishii, R. I. (2013). On adaptivity of online model selection method based on multikernel adaptive filtering. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 [6694329] https://doi.org/10.1109/APSIPA.2013.6694329

On adaptivity of online model selection method based on multikernel adaptive filtering. / Yukawa, Masahiro; Ishii, Ryu Ichiro.

2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013. 6694329.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yukawa, M & Ishii, RI 2013, On adaptivity of online model selection method based on multikernel adaptive filtering. in 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013., 6694329, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013, Kaohsiung, Taiwan, Province of China, 13/10/29. https://doi.org/10.1109/APSIPA.2013.6694329
Yukawa M, Ishii RI. On adaptivity of online model selection method based on multikernel adaptive filtering. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013. 6694329 https://doi.org/10.1109/APSIPA.2013.6694329
Yukawa, Masahiro ; Ishii, Ryu Ichiro. / On adaptivity of online model selection method based on multikernel adaptive filtering. 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013.
@inproceedings{cdc750223fe342da99e2488d0c9c599d,
title = "On adaptivity of online model selection method based on multikernel adaptive filtering",
abstract = "We investigate adaptivity of the online model selection method which has been proposed recently within the multikernel adaptive filtering framework. Specifically, we consider a situation in which the nonlinear system under study changes during adaptation and an appropriate kernel also does accordingly. Our time-varying cost functions involve three regularizers: the ℓ1 norm and two block ℓ1 norms which promote sparsity both in the kernel and data groups. The block ℓ1 regularizers are approximated by their Moreau envelopes, and the adaptive proximal forward-backward splitting (APFBS) method is applied to the approximated cost function. Numerical examples show that the proposed algorithm can adaptively estimate a reasonable model.",
author = "Masahiro Yukawa and Ishii, {Ryu Ichiro}",
year = "2013",
doi = "10.1109/APSIPA.2013.6694329",
language = "English",
isbn = "9789869000604",
booktitle = "2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013",

}

TY - GEN

T1 - On adaptivity of online model selection method based on multikernel adaptive filtering

AU - Yukawa, Masahiro

AU - Ishii, Ryu Ichiro

PY - 2013

Y1 - 2013

N2 - We investigate adaptivity of the online model selection method which has been proposed recently within the multikernel adaptive filtering framework. Specifically, we consider a situation in which the nonlinear system under study changes during adaptation and an appropriate kernel also does accordingly. Our time-varying cost functions involve three regularizers: the ℓ1 norm and two block ℓ1 norms which promote sparsity both in the kernel and data groups. The block ℓ1 regularizers are approximated by their Moreau envelopes, and the adaptive proximal forward-backward splitting (APFBS) method is applied to the approximated cost function. Numerical examples show that the proposed algorithm can adaptively estimate a reasonable model.

AB - We investigate adaptivity of the online model selection method which has been proposed recently within the multikernel adaptive filtering framework. Specifically, we consider a situation in which the nonlinear system under study changes during adaptation and an appropriate kernel also does accordingly. Our time-varying cost functions involve three regularizers: the ℓ1 norm and two block ℓ1 norms which promote sparsity both in the kernel and data groups. The block ℓ1 regularizers are approximated by their Moreau envelopes, and the adaptive proximal forward-backward splitting (APFBS) method is applied to the approximated cost function. Numerical examples show that the proposed algorithm can adaptively estimate a reasonable model.

UR - http://www.scopus.com/inward/record.url?scp=84893291282&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893291282&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2013.6694329

DO - 10.1109/APSIPA.2013.6694329

M3 - Conference contribution

SN - 9789869000604

BT - 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013

ER -