Local Convergence Analysis of FastICA

Date

2006

Authors

Shen, Hao
Hueper, Knut

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Abstract

The FastICA algorithm can be considered as a selfmap on a manifold. It turns out that FastICA is a scalar shifted version of an algorithm recently proposed. We put these algorithms into a dynamical system framework. The local convergence properties are investigated subject to an ideal ICA model. The analysis is very similar to the well-known case in numerical linear algebra when studying power iterations versus Rayleigh quotient iteration.

Description

Keywords

Keywords: Algorithms; Independent component analysis; Iterative methods; Linear algebra; Numerical linear algebra; Power iterations; Scalar shifted version; Blind source separation

Citation

Source

Type

Book chapter

Book Title

Independent Component Analysis and Blind Signal Separation

Entity type

Access Statement

License Rights

Restricted until