English

A Quasi-isometric Embedding Algorithm

Machine Learning 2017-11-06 v3 Computational Geometry Machine Learning

Abstract

The Whitney embedding theorem gives an upper bound on the smallest embedding dimension of a manifold. If a data set lies on a manifold, a random projection into this reduced dimension will retain the manifold structure. Here we present an algorithm to find a projection that distorts the data as little as possible.

Keywords

Cite

@article{arxiv.1709.01972,
  title  = {A Quasi-isometric Embedding Algorithm},
  author = {David W. Dreisigmeyer},
  journal= {arXiv preprint arXiv:1709.01972},
  year   = {2017}
}