Spline Embedding for Nonlinear Dimensionality Reduction

Abstract

This paper presents a new algorithm for nonlinear dimensionality reduction (NLDR). Smoothing splines are used to map the locally-coordinatized data points into a single global coordinate system of lower dimensionality. In this work setting, we can achieve two goals. First, a global embedding is obtained by minimizing the low-dimensional coordinate reconstruction error. Second, the NLDR algorithm can be naturally extended to deal with out-of-sample data points. Experimental results illustrate the validity of our method.

Cite

Text

Xiang et al. "Spline Embedding for Nonlinear Dimensionality Reduction." European Conference on Machine Learning, 2006. doi:10.1007/11871842_85

Markdown

[Xiang et al. "Spline Embedding for Nonlinear Dimensionality Reduction." European Conference on Machine Learning, 2006.](https://mlanthology.org/ecmlpkdd/2006/xiang2006ecml-spline/) doi:10.1007/11871842_85

BibTeX

@inproceedings{xiang2006ecml-spline,
  title     = {{Spline Embedding for Nonlinear Dimensionality Reduction}},
  author    = {Xiang, Shiming and Nie, Feiping and Zhang, Changshui and Zhang, Chunxia},
  booktitle = {European Conference on Machine Learning},
  year      = {2006},
  pages     = {825-832},
  doi       = {10.1007/11871842_85},
  url       = {https://mlanthology.org/ecmlpkdd/2006/xiang2006ecml-spline/}
}