Stochastic Neighbor Embedding separates well-separated clusters

02/09/2017
by   Uri Shaham, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset