FINDING CLUSTERS IN INDEPENDENT COMPONENT ANALYSIS

We present a class of algorithms that find clusters in independent component analysis: the data are linearly transformed so that the resulting components can be grouped into clusters, such that components are dependent within clusters and independent between clusters. In order to find such clusters, we look for a transform that fits the estimated sources to a forest-structured graphical model. In the nonGaussian, temporally independent case, the optimal transform is found by minimizing a contrast function based on mutual information that directly extends the contrast function used for classical ICA. We also derive a contrast function in theGaussian stationary case that is based on spectral densities and generalizes the contrast function of Pham [22] to richer classes of dependency.

[1]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[2]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[3]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[4]  Radim Jirousek,et al.  Solution of the marginal problem and decomposable distributions , 1991, Kybernetika (Praha).

[5]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[6]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[7]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[8]  D. Brillinger.  Remarks Concerning Graphical Models for Time Series and Point Processes , 1996 .

[9]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[10]  John N. Tsitsiklis,et al.  Introduction to linear optimization , 1997, Athena scientific optimization and computation series.

[11]  Andreas Ziehe,et al.  TDSEP — an efficient algorithm for blind separation using time structure , 1998 .

[12]  Alan Edelman,et al.  The Geometry of Algorithms with Orthogonality Constraints , 1998, SIAM J. Matrix Anal. Appl..

[13]  Jean-François Cardoso,et al.  Multidimensional independent component analysis , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[14]  Michael I. Jordan.  Graphical Models , 1998 .

[15]  Shotaro Akaho,et al.  MICA: multimodal independent component analysis , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[16]  Jean-Franois Cardoso.  High-Order Contrasts for Independent Component Analysis , 1999, Neural Computation.

[17]  R. Dahlhaus.  Graphical interaction models for multivariate time series1 , 2000 .

[18]  Aapo Hyvärinen,et al.  Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces , 2000, Neural Computation.

[19]  Michael I. Jordan,et al.  Tree-dependent Component Analysis , 2002, UAI.

[20]  Dinh-Tuan Pham,et al.  Mutual information approach to blind separation of stationary sources , 2002, IEEE Trans. Inf. Theory.

[21]  Michael I. Jordan,et al.  Kernel independent component analysis , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[22]  N. Davies.  Multiple Time Series , 2005 .