Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
7180979 | Probabilistic Engineering Mechanics | 2015 | 7 Pages |
Abstract
The paper examines the performance of the independent component analysis (ICA) which represents random vectors X by vectors XË whose components are linear forms of independent random variables. The representation holds exactly or asymptotically in tails for Gaussian and non-Gaussian vectors with special characteristic functions or Gaussian, translation, and non-Gaussian vectors with independent tails. However, the distributions of XË and its target vector X differ for a board range of non-Gaussian vectors. This statement is supported by numerical examples and theoretical arguments. It is also shown that the ICA representation XË is approximately Gaussian for high dimensional vectors.
Related Topics
Physical Sciences and Engineering
Engineering
Mechanical Engineering
Authors
H. Zhao, M. Grigoriu,