Hongyuan Zha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongyuan Zha has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Jesse L. Barlow
Department of Computer Science and Engineering Pennsylvania State University 343G IST Building 16802-6822 University Park PA USA
2 shared publications Zhenyue Zhang
Zhejiang University
2 shared publications- Chao-Hsien Chu
The Pennsylvania State University
1 shared publication Chris Ding
1 shared publication- Haesun Park
University of Minnesota
1 shared publication Horst Simon
1 shared publication
Latest Publications
- 31 January 2006
- Published by Elsevier in Expert Systems with Applications
- Vol. 30 (1) , 73-81
Splice site prediction using support vector machines with a Bayes kernel
- 31 January 2006
- Published by Elsevier in Expert Systems with Applications
- Vol. 30 (1) , 73-81
Splice site prediction using support vector machines with a Bayes kernel
- 1 December 2004
- Published by Springer Nature in Journal of Shanghai University (English Edition)
- Vol. 8 (4) , 406-424
Principal manifolds and nonlinear dimensionality reduction via tangent space alignment
- 1 December 2004
- Published by Springer Nature in Journal of Shanghai University (English Edition)
- Vol. 8 (4) , 406-424
Principal manifolds and nonlinear dimensionality reduction via tangent space alignment
- 27 August 2004
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 50 (1) , 1-4
2nd Special issue on matrix computations and statistics
- 27 August 2004
- Published by Elsevier in Computational Statistics & Data Analysis
- Vol. 50 (1) , 1-4
2nd Special issue on matrix computations and statistics
- Open Access
Principal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment
Nonlinear manifold learning from unorganized data points is a very challenging unsupervised learning and data visualization problem with a great variety of applications. In this paper we present a new algorithm for manifold learning and nonlinear dimension reduction. Based on a set of unorganized data points sampled with noise from the manifold, we represent the local geometry of the manifold using tangent spaces learned by fitting an affine subspace in a neighborhood of each data point. Those tangent spaces are aligned to give the internal global coordinates of the data points with respect to the underlying manifold by way of a partial eigendecomposition of the neighborhood connection matrix. We present a careful error analysis of our algorithm and show that the reconstruction errors are of second-order accuracy. We illustrate our algorithm using curves and surfaces both in 2D/3D and higher dimensional Euclidean spaces, and 64-by-64 pixel face images with various pose and lighting conditions. We also address several theoretical and algorithmic issues for further research and improvements.
Open AccessPrincipal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment
Nonlinear manifold learning from unorganized data points is a very challenging unsupervised learning and data visualization problem with a great variety of applications. In this paper we present a new algorithm for manifold learning and nonlinear dimension reduction. Based on a set of unorganized data points sampled with noise from the manifold, we represent the local geometry of the manifold using tangent spaces learned by fitting an affine subspace in a neighborhood of each data point. Those tangent spaces are aligned to give the internal global coordinates of the data points with respect to the underlying manifold by way of a partial eigendecomposition of the neighborhood connection matrix. We present a careful error analysis of our algorithm and show that the reconstruction errors are of second-order accuracy. We illustrate our algorithm using curves and surfaces both in 2D/3D and higher dimensional Euclidean spaces, and 64-by-64 pixel face images with various pose and lighting conditions. We also address several theoretical and algorithmic issues for further research and improvements.
- 1 March 1998
- Published by Springer Nature in BIT Numerical Mathematics
- Vol. 38 (1) , 200-216
Modifying the generalized singular value decomposition with application with application in direction-of-arrival finding
- 1 March 1998
- Published by Springer Nature in BIT Numerical Mathematics
- Vol. 38 (1) , 200-216
Modifying the generalized singular value decomposition with application with application in direction-of-arrival finding
- 1 February 1998
- Published by Elsevier in Linear Algebra and its Applications
- Vol. 270, 79-108
A sorted partial Jacobi method and its convergence analysis
- 1 February 1998
- Published by Elsevier in Linear Algebra and its Applications
- Vol. 270, 79-108
A sorted partial Jacobi method and its convergence analysis
- 1 March 1997
- Published by Springer Nature in BIT Numerical Mathematics
- Vol. 37 (1) , 202-220
Computing the optimal commuting matrix pairs
- 1 March 1997
- Published by Springer Nature in BIT Numerical Mathematics
- Vol. 37 (1) , 202-220
Computing the optimal commuting matrix pairs
- 1 March 1996
- Published by Springer Nature in BIT Numerical Mathematics
- Vol. 36 (1) , 14-40
An algorithm and a stability theory for downdating the ULV decomposition
- 1 March 1996
- Published by Springer Nature in BIT Numerical Mathematics
- Vol. 36 (1) , 14-40
An algorithm and a stability theory for downdating the ULV decomposition
- 1 January 1996
- Published by Springer Nature in Numerische Mathematik
- Vol. 72 (3) , 391-417
Computing the generalized singular values/vectors of large sparse or structured matrix pairs
- 1 January 1996
- Published by Springer Nature in Numerische Mathematik
- Vol. 72 (3) , 391-417
Computing the generalized singular values/vectors of large sparse or structured matrix pairs