Quasi-optimal EASI algorithm based on the Score Function Difference (SFD)

Equivariant Adaptive Separation via Independence (EASI) is one of the most successful algorithms for Blind Source Separation (BSS). However, the user has to choose nonlinearities, and usually simple (but non optimal) cubic polynomials are applied. In this paper, the optimal choice of these nonlinearities is addressed. We show that this optimal nonlinearity is the output Score Function Difference (SFD). Contrary to simple nonlinearities usually used in EASI (such as cubic polynomials), the optimal choice is neither component-wise nor fixed: it is a multivariate function which depends on the output distributions. Finally, we derive three adaptive algorithms for estimating the SFD and achieving "quasi-optimal" EASI algorithms, whose separation performance is much better than "standard" EASI and which especially converges for any sources.

• Type: Journal
• Year: 2006
• Where: IJON
• Authors: Samareh Samadi, Massoud Babaie-Zadeh, Christian Jutten
• Keywords: Cubic Polynomials, EASI, IJON 2006, Optimal Choice