Independent component analysis for tensor-valued data

Abstract

In preprocessing tensor-valued data, e.g. images and videos, a common procedure is to vectorize the observations and subject the resulting vectors to one of the many methods used for independent component analysis (ICA). However, the tensor structure of the original data is lost in the vectorization and, as a more suitable alternative, we propose the matrix- and tensor fourth order blind identification (MFOBI and TFOBI). In these tensorial extensions of the classic fourth order blind identification (FOBI) we assume a Kronecker structure for the mixing and perform FOBI simultaneously on each direction of the observed tensors. We discuss the theory and assumptions behind MFOBI and TFOBI and provide two different algorithms and related estimates of the unmixing matrices along with their asymptotic properties. Finally, simulations are used to compare the method's performance with that of classical FOBI for vectorized data and we end with a real data clustering example.

26 pages, 4 figures

References in corpus (6)

• On dimension folding of matrix- or array-valued statistical objects
• Asymptotic and bootstrap tests for subspace dimension
• Asymptotic and bootstrap tests for the dimension of the non-Gaussian subspace
• Robust Kronecker Product PCA for Spatio-Temporal Covariance Estimation
• Blind source separation of tensor-valued time series
• Joint Use of Third and Fourth Cumulants in Independent Component Analysis

Cited by in corpus (9)

• Graph Signal Processing Meets Blind Source Separation
• Independent component analysis for multivariate functional data
• Blind source separation of tensor-valued time series
• JADE for Tensor-Valued Observations
• Projected Estimation for Large-dimensional Matrix Factor Models
• Spatial Blind Source Separation in the Presence of a Drift
• Fast tensorial JADE
• Tensor Canonical Correlation Analysis with Convergence and Statistical Guarantees
• Independent vector analysis -- an introduction for statisticians