A unified view of adaptive variable-metric projection algorithms

Masahiro Yukawa, Isao Yamada

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

We present a unified analytic tool named variable-metric adaptive projected subgradient method (V-APSM) that encompasses the important family of adaptive variable-metric projection algorithms. The family includes the transform-domain adaptive filter, the Newton-method-based adaptive filters such as quasi-Newton, the proportionate adaptive filter, and the Krylov-proportionate adaptive filter. We provide a rigorous analysis of V-APSM regarding several invaluable properties including monotone approximation, which indicates stable tracking capability, and convergence to an asymptotically optimal point. Small metric-fluctuations are the key assumption for the analysis. Numerical examples show (i) the robustness of V-APSM against violation of the assumption and (ii) the remarkable advantages over its constant-metric counterpart for colored and nonstationary inputs under noisy situations.

Original languageEnglish
Article number589260
JournalEurasip Journal on Advances in Signal Processing
Volume2009
DOIs
Publication statusPublished - 2009
Externally publishedYes

Fingerprint

Adaptive filters
Newton-Raphson method
Mathematical transformations

ASJC Scopus subject areas

  • Hardware and Architecture
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

A unified view of adaptive variable-metric projection algorithms. / Yukawa, Masahiro; Yamada, Isao.

In: Eurasip Journal on Advances in Signal Processing, Vol. 2009, 589260, 2009.

Research output: Contribution to journalArticle

@article{7ad23c281f724dd9b91ccc8e45048356,
title = "A unified view of adaptive variable-metric projection algorithms",
abstract = "We present a unified analytic tool named variable-metric adaptive projected subgradient method (V-APSM) that encompasses the important family of adaptive variable-metric projection algorithms. The family includes the transform-domain adaptive filter, the Newton-method-based adaptive filters such as quasi-Newton, the proportionate adaptive filter, and the Krylov-proportionate adaptive filter. We provide a rigorous analysis of V-APSM regarding several invaluable properties including monotone approximation, which indicates stable tracking capability, and convergence to an asymptotically optimal point. Small metric-fluctuations are the key assumption for the analysis. Numerical examples show (i) the robustness of V-APSM against violation of the assumption and (ii) the remarkable advantages over its constant-metric counterpart for colored and nonstationary inputs under noisy situations.",
author = "Masahiro Yukawa and Isao Yamada",
year = "2009",
doi = "10.1155/2009/589260",
language = "English",
volume = "2009",
journal = "Eurasip Journal on Advances in Signal Processing",
issn = "1687-6172",
publisher = "Springer Publishing Company",

}

TY - JOUR

T1 - A unified view of adaptive variable-metric projection algorithms

AU - Yukawa, Masahiro

AU - Yamada, Isao

PY - 2009

Y1 - 2009

N2 - We present a unified analytic tool named variable-metric adaptive projected subgradient method (V-APSM) that encompasses the important family of adaptive variable-metric projection algorithms. The family includes the transform-domain adaptive filter, the Newton-method-based adaptive filters such as quasi-Newton, the proportionate adaptive filter, and the Krylov-proportionate adaptive filter. We provide a rigorous analysis of V-APSM regarding several invaluable properties including monotone approximation, which indicates stable tracking capability, and convergence to an asymptotically optimal point. Small metric-fluctuations are the key assumption for the analysis. Numerical examples show (i) the robustness of V-APSM against violation of the assumption and (ii) the remarkable advantages over its constant-metric counterpart for colored and nonstationary inputs under noisy situations.

AB - We present a unified analytic tool named variable-metric adaptive projected subgradient method (V-APSM) that encompasses the important family of adaptive variable-metric projection algorithms. The family includes the transform-domain adaptive filter, the Newton-method-based adaptive filters such as quasi-Newton, the proportionate adaptive filter, and the Krylov-proportionate adaptive filter. We provide a rigorous analysis of V-APSM regarding several invaluable properties including monotone approximation, which indicates stable tracking capability, and convergence to an asymptotically optimal point. Small metric-fluctuations are the key assumption for the analysis. Numerical examples show (i) the robustness of V-APSM against violation of the assumption and (ii) the remarkable advantages over its constant-metric counterpart for colored and nonstationary inputs under noisy situations.

UR - http://www.scopus.com/inward/record.url?scp=76649099789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76649099789&partnerID=8YFLogxK

U2 - 10.1155/2009/589260

DO - 10.1155/2009/589260

M3 - Article

AN - SCOPUS:76649099789

VL - 2009

JO - Eurasip Journal on Advances in Signal Processing

JF - Eurasip Journal on Advances in Signal Processing

SN - 1687-6172

M1 - 589260

ER -