In search of non-Gaussian components of a high-dimensional distribution
Authors
- Blanchard, Gilles
- Kawanabe, Motoaki
- Sugiyama, Masashi
- Spokoiny, Vladimir
ORCID: 0000-0002-2040-3427 - Müller, Klaus-Robert
2010 Mathematics Subject Classification
- 00A73 62H30 62H99 68Q32
Keywords
- Non-Gaussian components, dimension reduction
DOI
Abstract
Finding non-Gaussian components of high-dimensional data is an important preprocessing step for efficient information processing. This article proposes a new em linear method to identify the ``non-Gaussian subspace'' within a very general semi-parametric framework. Our proposed method, called NGCA (Non-Gaussian Component Analysis), is essentially based on the fact that we can construct a linear operator which, to any arbitrary nonlinear (smooth) function, associates a vector which belongs to the low dimensional non-Gaussian target subspace up to an estimation error. By applying this operator to a family of different nonlinear functions, one obtains a family of different vectors lying in a vicinity of the target space. As a final step, the target space itself is estimated by applying PCA to this family of vectors. We show that this procedure is consistent in the sense that the estimaton error tends to zero at a parametric rate, uniformly over the family, Numerical examples demonstrate the usefulness of our method.
Appeared in
- J. Mach. Learn. Res., 7 (2006) pp. 247--282.
Download Documents