Non-Gaussian component analysis using entropy methods

DOI10.1145/3313276.3316309MaRDI QIDQ5212824zbMATH OpenOpenAlexFDO

Authors Navin Goyal, Abhishek Shetty

Publication date 30 January 2020

Published in Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1807.04936

zbMATH Keywords

entropynon-Gaussian component analysisprojection pursuit

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Factor analysis and principal components; correspondence analysis (62H25) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: Non-Gaussian component analysis (NGCA) is a problem in multidimensional data analysis which, since its formulation in 2006, has attracted considerable attention in statistics and machine learning. In this problem, we have a random variable $X$ in $n$-dimensional Euclidean space. There is an unknown subspace $Gamma$ of the $n$-dimensional Euclidean space such that the orthogonal projection of $X$ onto $Gamma$ is standard multidimensional Gaussian and the orthogonal projection of $X$ onto $Gamm{a}^{perp}$, the orthogonal complement of $Gamma$, is non-Gaussian, in the sense that all its one-dimensional marginals are different from the Gaussian in a certain metric defined in terms of moments. The NGCA problem is to approximate the non-Gaussian subspace $Gamm{a}^{perp}$ given samples of $X$. Vectors in $Gamm{a}^{perp}$ correspond to `interesting' directions, whereas vectors in $Gamma$ correspond to the directions where data is very noisy. The most interesting applications of the NGCA model is for the case when the magnitude of the noise is comparable to that of the true signal, a setting in which traditional noise reduction techniques such as PCA don't apply directly. NGCA is also related to dimension reduction and to other data analysis problems such as ICA. NGCA-like problems have been studied in statistics for a long time using techniques such as projection pursuit. We give an algorithm that takes polynomial time in the dimension $n$ and has an inverse polynomial dependence on the error parameter measuring the angle distance between the non-Gaussian subspace and the subspace output by the algorithm. Our algorithm is based on relative entropy as the contrast function and fits under the projection pursuit framework. The techniques we develop for analyzing our algorithm maybe of use for other related problems.

Recommendations

• In search of non-Gaussian components of a high-dimensional distribution
• Independent Component Analysis and Blind Signal Separation
• A new algorithm of non-Gaussian component analysis with radial kernel functions
• Non-Gaussian component analysis: testing the dimension of the signal subspace
• Independent Component Analysis and Blind Signal Separation

Cited in

(12)

• In search of non-Gaussian components of a high-dimensional distribution
• Sparse non Gaussian component analysis by semidefinite programming
• ECA: High-Dimensional Elliptical Component Analysis in Non-Gaussian Distributions
• Compressed principal component analysis of non-Gaussian vectors
• Non-Gaussian component analysis: testing the dimension of the signal subspace
• Optimal partition in terms of independent random vectors of any non-Gaussian vector defined by a set of realizations
• Independent Component Analysis and Blind Signal Separation
• Independent Component Analysis and Blind Signal Separation
• Independent Component Analysis and Blind Signal Separation
• Statistical-computational trade-offs in tensor PCA and related problems via communication complexity
• Optimal spectral recovery of a planted vector in a subspace
• A new algorithm of non-Gaussian component analysis with radial kernel functions

This page was built for publication: Non-Gaussian component analysis using entropy methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5212824)