Randomized Independent Component Analysis

TL;DR

This paper introduces randomized measures for independent component analysis that significantly reduce computational complexity while maintaining high separation accuracy, enabling faster ICA decomposition.

Contribution

It proposes novel randomized measures for ICA that approximate kernel-based methods with linear complexity, improving efficiency without sacrificing performance.

Findings

Randomized measures achieve comparable separation accuracy to kernel-based methods.

The proposed methods are an order of magnitude faster in optimization.

Computational complexity is reduced from cubic to linear in sample size.

Abstract

Independent component analysis (ICA) is a method for recovering statistically independent signals from observations of unknown linear combinations of the sources. Some of the most accurate ICA decomposition methods require searching for the inverse transformation which minimizes different approximations of the Mutual Information, a measure of statistical independence of random vectors. Two such approximations are the Kernel Generalized Variance or the Kernel Canonical Correlation which has been shown to reach the highest performance of ICA methods. However, the computational effort necessary just for computing these measures is cubic in the sample size. Hence, optimizing them becomes even more computationally demanding, in terms of both space and time. Here, we propose a couple of alternative novel measures based on randomized features of the samples - the Randomized Generalized Variance and the Randomized Canonical Correlation. The computational complexity of calculating the proposed alternatives is linear in the sample size and provide a controllable approximation of their Kernel-based non-random versions. We also show that optimization of the proposed statistical properties yields a comparable separation error at an order of magnitude faster compared to Kernel-based measures.