One-Bit-Matching ICA Theorem, Convex-Concave Programming, and Combinatorial Optimization

Recently, a mathematical proof is obtained in (Liu, Chiu, Xu, 2004) on the so called one-bit-matching conjecture that all the sources can be separated as long as there is an one-to-one same-signcorrespondence between the kurtosis signs of all source probability density functions (pdf’s) and the kurtosis signs of all model pdf’s (Xu, Cheung, Amari, 1998a), which is widely believed and implicitly supported by many empirical studies. However, this proof is made only in a weak sense that the conjecture is true when the global optimal solution of an ICA criterion is reached. Thus, it can not support the successes of many existing iterative algorithms that usually converge at one of local optimal solutions. In this paper, a new mathematical proof is obtained in a strong sense that the conjecture is also true when anyone of local optimal solutions is reached, in help of investigating convex-concave programming on a polyhedral-set. Theorems have also been proved not only on partial separat...

• Type: Conference
• Year: 2005
• Where: ISNN
• Authors: Lei Xu
• Keywords: ISNN 2005, Kurtosis Signs, Mathematical Proof, Optimal Solutions