Stochastic Neighbor Embedding separates well-separated clusters
Machine Learning
2017-02-24 v2 Statistics Theory
Statistics Theory
Abstract
Stochastic Neighbor Embedding and its variants are widely used dimensionality reduction techniques -- despite their popularity, no theoretical results are known. We prove that the optimal SNE embedding of well-separated clusters from high dimensions to any Euclidean space R^d manages to successfully separate the clusters in a quantitative way. The result also applies to a larger family of methods including a variant of t-SNE.
Cite
@article{arxiv.1702.02670,
title = {Stochastic Neighbor Embedding separates well-separated clusters},
author = {Uri Shaham and Stefan Steinerberger},
journal= {arXiv preprint arXiv:1702.02670},
year = {2017}
}