Title :
Sparse Non-Gaussian Component Analysis
Author :
Diederichs, Elmar ; Juditsky, Anatoli ; Spokoiny, Vladimir ; Schütte, Christof
Author_Institution :
Inst. for Math. & Inf., Free Univ. Berlin, Berlin, Germany
fDate :
6/1/2010 12:00:00 AM
Abstract :
Non-Gaussian component analysis (NGCA) introduced in offered a method for high-dimensional data analysis allowing for identifying a low-dimensional non-Gaussian component of the whole distribution in an iterative and structure adaptive way. An important step of the NGCA procedure is identification of the non-Gaussian subspace using principle component analysis (PCA) method. This article proposes a new approach to NGCA called sparse NGCA which replaces the PCA-based procedure with a new the algorithm we refer to as convex projection.
Keywords :
Gaussian noise; iterative methods; principal component analysis; sparse matrices; convex projection; high-dimensional data analysis; iterative way; nonGaussian subspace; principle component analysis; sparse nonGaussian component analysis; structure adaptive way; Biology computing; Data analysis; Gaussian noise; Input variables; Iterative algorithms; Iterative methods; Least squares approximation; Principal component analysis; Reduced order systems; Statistical analysis; Convex projection; model reduction; principle component analysis (PCA); reduction of dimensionality; sparsity; structural adaptation; variable selection;
Journal_Title :
Information Theory, IEEE Transactions on
DOI :
10.1109/TIT.2010.2046229
