Matrix perturbation analysis of local tangent space alignment

Abstract We consider the performance of Local Tangent Space Alignment (Zhang & Zha [1]), one of several manifold learning algorithms, which have been proposed as a dimension reduction method. Matrix perturbation theory is applied to obtain a worst-case upper bound on the angle between the computed linear invariant subspace and the linear invariant subspace that is associated with the embedded intrinsic parametrization. Our result is the first performance bound that has been derived.

[1]  Matthew Brand,et al.  Charting a Manifold , 2002, NIPS.

[2]  Evangelos Triantaphyllou,et al.  Recent Advances in Data Mining of Enterprise Data: Algorithms and Applications , 2008, Series on Computers and Operations Research.

[3]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[4]  Anja Vogler,et al.  An Introduction to Multivariate Statistical Analysis , 2004 .

[5]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[6]  Hongyuan Zha,et al.  Spectral analysis of alignment in manifold learning , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[7]  G. Stewart,et al.  Matrix Perturbation Theory , 1990 .

[8]  Hongyuan Zha,et al.  Principal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment , 2002, ArXiv.

[9]  Performance Analysis of a Manifold Learning Algorithm in Dimension Reduction , 2006 .

[10]  D. Donoho,et al.  Hessian Eigenmaps : new locally linear embedding techniques for high-dimensional data , 2003 .

[11]  H. Zha,et al.  Principal manifolds and nonlinear dimensionality reduction via tangent space alignment , 2004, SIAM J. Sci. Comput..

[12]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[13]  X. Huo,et al.  Chapter A Survey of Manifold-Based Learning Methods , 2007 .

[14]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[15]  D. Donoho,et al.  Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data , 2003, Proceedings of the National Academy of Sciences of the United States of America.