Space-Time Local Embeddings

Abstract

Space-time is a profound concept in physics. This concept was shown to be useful for dimensionality reduction. We present basic definitions with interesting counter-intuitions. We give theoretical propositions to show that space-time is a more powerful representation than Euclidean space. We apply this concept to manifold learning for preserving local information. Empirical results on non-metric datasets show that more information can be preserved in space-time.

Cite

Text

Sun et al. "Space-Time Local Embeddings." Neural Information Processing Systems, 2015.

Markdown

[Sun et al. "Space-Time Local Embeddings." Neural Information Processing Systems, 2015.](https://mlanthology.org/neurips/2015/sun2015neurips-spacetime/)

BibTeX

@inproceedings{sun2015neurips-spacetime,
  title     = {{Space-Time Local Embeddings}},
  author    = {Sun, Ke and Wang, Jun and Kalousis, Alexandros and Marchand-Maillet, Stephane},
  booktitle = {Neural Information Processing Systems},
  year      = {2015},
  pages     = {100-108},
  url       = {https://mlanthology.org/neurips/2015/sun2015neurips-spacetime/}
}