Simultaneous Estimation of Nongaussian Components and their Correlation Structure

Hiroaki Sasaki, Michael Gutmann, Hayaru Shouno, Aapo Hyvärinen

Research output: Contribution to journalArticlepeer-review


The statistical dependencies which independent component analysis (ICA) cannot remove often provide rich information beyond the linear independent components. It would thus be very useful to estimate the dependency structure from data. While such models have been proposed, they usually concentrated on higher-order correlations such as energy (square) correlations. Yet, linear correlations are a most fundamental and informative form of dependency in many real data sets. Linear correlations are usually completely removed by ICA and related methods, so they can only be analyzed by developing new methods which explicitly allow for linearly correlated components. In this paper, we propose a probabilistic model of linear non-Gaussian components which are allowed to have both linear and energy correlations. The precision matrix of the
linear components is assumed to be randomly generated by a higher-order process and explicitly parametrized by a parameter matrix. The estimation of the parameter matrix is shown to be particularly simple because using score matching (Hyvaerinen, 2005), the objective function is a quadratic form. Using simulations with artificial data, we demonstrate that the proposed method improves identifiability of non-Gaussian components by simultaneously learning their correlation structure. Applications on simulated complex cells with natural image input, as well as spectrograms of natural audio data show that the method finds new kinds of dependencies between the components.
Original languageEnglish
Number of pages54
JournalNeural Computation
Early online date4 Aug 2017
Publication statusE-pub ahead of print - 4 Aug 2017


Dive into the research topics of 'Simultaneous Estimation of Nongaussian Components and their Correlation Structure'. Together they form a unique fingerprint.

Cite this