Colored subspace analysis

Colored subspace analysis

With the advent of high-throughput data recording methods in biology and medicine, the efficient identification of meaningful subspaces within these data sets becomes an increasingly important challenge. Classical dimension reduction techniques such as principal component analysis often do not take the rich statistics of real-world data into account, and thereby fail if the signal space is for example of low power but meaningful in terms of some other statistics. With 'colored subspace analysis', we propose a method for linear dimension reduction that evaluates the time structure of the multivariate observations. We differentiate the signal subspace from noise by searching for a subspace of non-trivially autocorrelated data. We can prove that the resulting signal subspace is uniquely determined by the data, given that all white components have been removed. Algorithmically we propose three methods to perform this search, based on joint diagonalization, using a component clustering scheme, and via joint low-rank approximation. In contrast to temporal mixture approaches from blind signal processing we do not need a generative model, i.e. we do not require the existence of sources, so the model is applicable to any wide-sense stationary time series without restrictions. Moreover, since the method is based on second-order time structure, it can be efficiently implemented and applied even in large dimensions.

Source code

You can download the CSA Matlab sources here.

We use cookies to improve your experience on our Website. We need cookies to continuously improve the services, to enable certain features and when embedding services or content of third parties, such as video player. By using our website, you agree to the use of cookies. We use different types of cookies. You can personalize your cookie settings here:

Show detail settings
Please find more information in our privacy statement.

There you may also change your settings later.