An efficient parameter optimization of maximum correntropy criterion

Long Shi; Lu Shen; Badong Chen

doi:10.1109/LSP.2023.3273174

An efficient parameter optimization of maximum correntropy criterion

Long Shi^*, Lu Shen, Badong Chen

^*Corresponding author for this work

Electronic Engineering

Research output: Contribution to journal › Letter › peer-review

Abstract

The maximum correntropy criterion (MCC) algorithm depends upon two fundamental parameters, i.e., step-size and kernel width. Previous studies of parameter optimization in the MCC mainly focus on a single parameter (mainly the kernel width), lacking optimization research concerning both parameters. To this end, this letter investigates a novel optimization scheme simultaneously involving step-size and kernel width. The optimization framework is based on making the power of weight error vector undergo the steepest attenuation. Under the premise of maintaining the same evolutionary trend for time-varying step-size and kernel width, we formulate a constrained parameter optimization problem, where
the step-size is subject to a kernel width induced constraint. By taking this approach, the original bivariate optimization can be transformed into a univariate optimization problem, which facilitates optimization solving. We further develop an existing reset scheme to make it suitable for kernel width to ensure a good tracking capability. In addition, we investigate the convergence behavior of the optimized algorithm. Simulation results demonstrate that the developed optimization scheme is beneficial for performance improvement, and the resulting algorithm outperforms some state-of-art MCC-based algorithms.

Original language	English
Pages (from-to)	538-542
Journal	IEEE Signal Processing Letters
Volume	30
DOIs	https://doi.org/10.1109/LSP.2023.3273174
Publication status	Published - 4 May 2023

Access to Document

10.1109/LSP.2023.3273174

Cite this

@article{7debaf8a09a4435e8b62a7e973e2e1a8,

title = "An efficient parameter optimization of maximum correntropy criterion",

abstract = "The maximum correntropy criterion (MCC) algorithm depends upon two fundamental parameters, i.e., step-size and kernel width. Previous studies of parameter optimization in the MCC mainly focus on a single parameter (mainly the kernel width), lacking optimization research concerning both parameters. To this end, this letter investigates a novel optimization scheme simultaneously involving step-size and kernel width. The optimization framework is based on making the power of weight error vector undergo the steepest attenuation. Under the premise of maintaining the same evolutionary trend for time-varying step-size and kernel width, we formulate a constrained parameter optimization problem, wherethe step-size is subject to a kernel width induced constraint. By taking this approach, the original bivariate optimization can be transformed into a univariate optimization problem, which facilitates optimization solving. We further develop an existing reset scheme to make it suitable for kernel width to ensure a good tracking capability. In addition, we investigate the convergence behavior of the optimized algorithm. Simulation results demonstrate that the developed optimization scheme is beneficial for performance improvement, and the resulting algorithm outperforms some state-of-art MCC-based algorithms.",

author = "Long Shi and Lu Shen and Badong Chen",

year = "2023",

month = may,

day = "4",

doi = "10.1109/LSP.2023.3273174",

language = "English",

volume = "30",

pages = "538--542",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "IEEE",

}

TY - JOUR

T1 - An efficient parameter optimization of maximum correntropy criterion

AU - Shi, Long

AU - Shen, Lu

AU - Chen, Badong

PY - 2023/5/4

Y1 - 2023/5/4

N2 - The maximum correntropy criterion (MCC) algorithm depends upon two fundamental parameters, i.e., step-size and kernel width. Previous studies of parameter optimization in the MCC mainly focus on a single parameter (mainly the kernel width), lacking optimization research concerning both parameters. To this end, this letter investigates a novel optimization scheme simultaneously involving step-size and kernel width. The optimization framework is based on making the power of weight error vector undergo the steepest attenuation. Under the premise of maintaining the same evolutionary trend for time-varying step-size and kernel width, we formulate a constrained parameter optimization problem, wherethe step-size is subject to a kernel width induced constraint. By taking this approach, the original bivariate optimization can be transformed into a univariate optimization problem, which facilitates optimization solving. We further develop an existing reset scheme to make it suitable for kernel width to ensure a good tracking capability. In addition, we investigate the convergence behavior of the optimized algorithm. Simulation results demonstrate that the developed optimization scheme is beneficial for performance improvement, and the resulting algorithm outperforms some state-of-art MCC-based algorithms.

AB - The maximum correntropy criterion (MCC) algorithm depends upon two fundamental parameters, i.e., step-size and kernel width. Previous studies of parameter optimization in the MCC mainly focus on a single parameter (mainly the kernel width), lacking optimization research concerning both parameters. To this end, this letter investigates a novel optimization scheme simultaneously involving step-size and kernel width. The optimization framework is based on making the power of weight error vector undergo the steepest attenuation. Under the premise of maintaining the same evolutionary trend for time-varying step-size and kernel width, we formulate a constrained parameter optimization problem, wherethe step-size is subject to a kernel width induced constraint. By taking this approach, the original bivariate optimization can be transformed into a univariate optimization problem, which facilitates optimization solving. We further develop an existing reset scheme to make it suitable for kernel width to ensure a good tracking capability. In addition, we investigate the convergence behavior of the optimized algorithm. Simulation results demonstrate that the developed optimization scheme is beneficial for performance improvement, and the resulting algorithm outperforms some state-of-art MCC-based algorithms.

U2 - 10.1109/LSP.2023.3273174

DO - 10.1109/LSP.2023.3273174

M3 - Letter

SN - 1070-9908

VL - 30

SP - 538

EP - 542

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

ER -