Stochastic Neighbor Embedding separates well-separated clusters
Shaham, Uri, Steinerberger, Stefan
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.
Feb-22-2017
- Country:
- Europe > Spain (0.14)
- North America
- Canada (0.14)
- Puerto Rico (0.14)
- United States (0.14)
- Genre:
- Research Report (0.40)
- Technology: