Analysis of feasible solutions of the ICA problem under the one-bit-matching condition

Authors:
Jinwen Ma;Zhe Chen;Shun-ichi Amari
Affiliations:
Laboratory of Mathematical Neuroscience;Laboratory of Advanced Brain Signal Processing, RIKEN Brain Science Institute, Saitama, Japan;Laboratory of Mathematical Neuroscience
Venue:
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
Year:
2006

Citing 10
Cited 1

Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Adaptive blind separation of independent sources: a deflation approach

Signal Processing
An information-maximization approach to blind separation and blind deconvolution

Neural Computation
An alternative perspective on adaptive independent component analysis algorithms

Neural Computation
The Geometry of Algorithms with Orthogonality Constraints

SIAM Journal on Matrix Analysis and Applications
Independent component analysis: a flexible nonlinearity and decorrelating manifold approach

Neural Computation
A Further Result on the ICA One-Bit-Matching Conjecture

Neural Computation
One-Bit-Matching Conjecture for Independent Component Analysis

Neural Computation
A Constrained EM Algorithm for Independent Component Analysis

Neural Computation
Letters: An alternative switching criterion for independent component analysis (ICA)

Neurocomputing

Analysis of the Kurtosis-Sum Objective Function for ICA

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The one-bit-matching conjecture for independent component analysis (ICA) has been widely believed in the ICA community. Theoretically, it has been proved that under certain regular assumptions, the global maximum of a simplified objective function derived from the maximum likelihood or minimum mutual information criterion under the one-bit-matching condition corresponds to a feasible solution of the ICA problem, and also that all the local maxima of the objective function correspond to the feasible solutions of the ICA problem in the two-source square mixing setting. This paper further studies the one-bit-matching conjecture along this direction, and we prove that under the one-bit-matching condition there always exist many local maxima of the objective function that correspond to the stable feasible solutions of the ICA problem in the general case; moreover, in ceratin cases there also exist some local minima of the objective function that correspond to the stable feasible solutions of the ICA problem with mixed super- and sub-Gaussian sources.