PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

How fast is FastICA
Vicente Zarzoso and Pierre Comon
In: 14th European Signal Processing Conference (EUSIPCO), September 4-8, 2006, Firenze, Italy.

Abstract

The present contribution deals with the statistical tool of Independent Component Analysis (ICA). The focus is on the deflation approach, whereby the independent components are extracted one after another. The kurtosis-based FastICA is arguably one of the most widespread methods of this kind. However, its features, particularly its speed, have not been thoroughly evaluated or compared, so that its popularity seems somewhat unfounded. To substantiate this claim, a simple quite natural modification is put forward and assessed in this paper. It merely consists of performing exact line search optimization of the contrast function. Speed is objectively measured in terms of the computational complexity required to reach a given source extraction performance. Illustrative numerical results demonstrate the faster convergence and higher robustness to initialization of the proposed approach, which is thus referred to as RobustICA.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Lecture)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:2323
Deposited By:Pierre Comon
Deposited On:22 November 2006