Convergence analysis of a modified Armijo rule step-size LMF algorithm

Syed Muhammad Asad*, Azzedine Zerguine

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

In this work, we make use of the Armijo rule for the selection of the learning rate to introduce the Armijo rule learning rate least mean fourth (ALRLMF) algorithm. The algorithm is derived by incorporating the modified version of the Armijo rule line search to the class of stochastic gradient algorithm that minimizes the mean fourth error. The convergence behavior of the algorithm is analyzed and bounds guaranteeing convergence are explicitly derived. Finally, simulation results presented in a system identification scenario are found to corroborate the theoretical findings.

Original languageEnglish
Title of host publication2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012
Pages343-347
Number of pages5
DOIs
StatePublished - 2012

Publication series

Name2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012

Keywords

  • Adaptive Filters
  • Armijo Rule LMF
  • LMF

ASJC Scopus subject areas

  • Computer Science Applications
  • Signal Processing

Fingerprint

Dive into the research topics of 'Convergence analysis of a modified Armijo rule step-size LMF algorithm'. Together they form a unique fingerprint.

Cite this