Fixed Point Algorithms for Estimating Power Means of Positive Definite Matrices

Estimating means of data points lying on the Riemannian manifold of symmetric positive-definite (SPD) matrices has proved of great utility in applications requiring interpolation, extrapolation, smoothing, signal detection, and classification. The power means of SPD matrices with exponent p in the interval [–1, 1] interpolate in between the Harmonic mean (p = –1) and the Arithmetic mean (p = 1), while the Geometric (Cartan/Karcher) mean, which is the one currently employed in most applications, corresponds to their limit evaluated at 0. In this paper, we treat the problem of estimating power means along the continuum p ∊ (–1, 1) given noisy observed measurement. We provide a general fixed point algorithm (MPM) and we show that its convergence rate for p = ±0.5 deteriorates very little with the number and dimension of points given as input. Along the whole continuum, MPM is also robust with respect to the dispersion of the points on the manifold (noise), much more than the gradient descent algorithm usually employed to estimate the geometric mean. Thus, MPM is an efficient algorithm for the whole family of power means, including the geometric mean, which by MPM can be approximated with a desired precision by interpolating two solutions obtained with a small ±p value. We also present an approximated version of the MPM algorithm with very low computational complexity for the special case p = ±½. Finally, we show the appeal of power means through the classification of brain–computer interface event-related potentials data.

[1]  Christian Jutten,et al.  Classification of covariance matrices using a Riemannian-based kernel for BCI applications , 2013, Neurocomputing.

[2]  Marc Arnaudon,et al.  A stochastic algorithm finding generalized means on compact manifolds , 2013, 1305.6295.

[3]  Maher Moakher,et al.  Means of Hermitian positive-definite matrices based on the log-determinant α-divergence function , 2012 .

[4]  Yongdo Lim,et al.  Weighted means and Karcher equations of positive operators , 2013, Proceedings of the National Academy of Sciences.

[5]  Nicholas Ayache,et al.  Geometric Means in a Novel Vector Space Structure on Symmetric Positive-Definite Matrices , 2007, SIAM J. Matrix Anal. Appl..

[6]  Christian Jutten,et al.  " Brain Invaders": a prototype of an open-source P300-based video game working with the OpenViBE platform , 2011 .

[7]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[8]  Maher Moakher.  On the Averaging of Symmetric Positive-Definite Tensors , 2006 .

[9]  Alan J. Laub,et al.  On Scaling Newton's Method for Polar Decomposition and the Matrix Sign Function , 1990, 1990 American Control Conference.

[10]  Pawel Zielinski,et al.  On iterative algorithms for the polar decomposition of a matrix and the matrix sign function , 2015, Appl. Math. Comput..

[11]  Christian Jutten,et al.  Multiclass Brain–Computer Interface Classification by Riemannian Geometry , 2012, IEEE Transactions on Biomedical Engineering.

[12]  Kon Max Wong,et al.  Riemannian Distances for Signal Classification by Power Spectral Density , 2013, IEEE Journal of Selected Topics in Signal Processing.

[13]  Mikl'os P'alfia,et al.  Operator means of probability measures and generalized Karcher equations , 2016, 1601.06777.

[14]  Y. Lim,et al.  Monotonic properties of the least squares mean , 2010, 1007.4792.

[15]  R. Bhatia,et al.  Riemannian geometry and matrix geometric means , 2006 .

[16]  R. Bhatia.  Positive Definite Matrices , 2007 .

[17]  Chi-Kwong Li.  Geometric Means , 2003 .

[18]  Maher Moakher,et al.  A Differential Geometric Approach to the Geometric Mean of Symmetric Positive-Definite Matrices , 2005, SIAM J. Matrix Anal. Appl..

[19]  Tryphon T. Georgiou,et al.  Distances and Riemannian Metrics for Spectral Density Functions , 2007, IEEE Transactions on Signal Processing.

[20]  Christian Jutten,et al.  Parameters estimate of Riemannian Gaussian distribution in the manifold of covariance matrices , 2016, 2016 IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM).

[21]  Y. Lim,et al.  Matrix power means and the Karcher mean , 2012 .

[22]  Maher Moakher,et al.  The Riemannian Geometry of the Space of Positive-Definite Matrices and Its Application to the Regularization of Positive-Definite Matrix-Valued Data , 2011, Journal of Mathematical Imaging and Vision.

[23]  Christian Jutten,et al.  Single-trial classification of multi-user P300-based Brain-Computer Interface using riemannian geometry , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  M. Congedo,et al.  Approximate Joint Diagonalization and Geometric Mean of Symmetric Positive Definite Matrices , 2015, PloS one.

[25]  Yin Wang,et al.  Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Ronald Phlypo,et al.  A Fixed-Point Algorithm for Estimating Power Means of Positive Definite Matrices , 2016 .

[27]  24th European Signal Processing Conference, EUSIPCO 2016, Budapest, Hungary, August 29 - September 2, 2016 , 2016, European Signal Processing Conference.

[28]  Tryphon T. Georgiou,et al.  Distances and Riemannian Metrics for Multivariate Spectral Densities , 2011, IEEE Transactions on Automatic Control.

[29]  B. Parlett.  A recurrence among the elements of functions of triangular matrices , 1976 .

[30]  Jonathan H. Manton,et al.  Riemannian Gaussian Distributions on the Space of Symmetric Positive Definite Matrices , 2015, IEEE Transactions on Information Theory.

[31]  Teng Zhang.  A Majorization-Minimization Algorithm for the Karcher Mean of Positive Definite Matrices , 2013 .

[32]  Suresh Venkatasubramanian,et al.  The geometric median on Riemannian manifolds with application to robust atlas estimation , 2009, NeuroImage.

[33]  Emmanuel K. Kalunga,et al.  Online SSVEP-based BCI using Riemannian geometry , 2015, Neurocomputing.

[34]  Jimmie D. Lawson,et al.  Karcher means and Karcher equations of positive definite operators , 2014 .

[35]  Marc Arnaudon,et al.  A stochastic algorithm finding $p$-means on the circle , 2013, 1301.7156.

[36]  Nicholas J. Higham,et al.  A Schur-Parlett Algorithm for Computing Matrix Functions , 2003, SIAM J. Matrix Anal. Appl..

[37]  René Vidal,et al.  On the Convergence of Gradient Descent for Finding the Riemannian Center of Mass , 2011, SIAM J. Control. Optim..

[38]  Nicholas Ayache,et al.  A Riemannian Framework for the Processing of Tensor-Valued Images , 2005, DSSCV.

[39]  Nicholas J. Higham,et al.  Stable iterations for the matrix square root , 1997, Numerical Algorithms.

[40]  F. Barbaresco.  Information Geometry of Covariance Matrix: Cartan-Siegel Homogeneous Bounded Domains, Mostow/Berger Fibration and Fréchet Median , 2013 .

[41]  Mehrtash Tafazzoli Harandi,et al.  More about VLAD: A leap from Euclidean to Riemannian manifolds , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Marc Arnaudon,et al.  Riemannian Medians and Means With Applications to Radar Signal Processing , 2013, IEEE Journal of Selected Topics in Signal Processing.

[43]  Ben Jeuris,et al.  A survey and comparison of contemporary algorithms for computing the matrix geometric mean , 2012 .

[45]  S. Sra.  Positive definite matrices and the S-divergence , 2011, 1110.1773.

[46]  Noboru Nakamura,et al.  Geometric Means of Positive Operators , 2009 .

[47]  Marco Congedo,et al.  EEG Source Analysis , 2013 .

[48]  P. Thomas Fletcher,et al.  Geodesic Regression and the Theory of Least Squares on Riemannian Manifolds , 2012, International Journal of Computer Vision.