A Quasi-isometric Embedding Algorithm

2017/09/06 by Dreisigmeyer, David W.
#Computational Geometry (cs.CG) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1709.01972

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.

Related

• Stable Manifold Embeddings with Structured Random Matrices
• Manifold-aligned Neighbor Embedding
• Learning low bending and low distortion manifold embeddings
• Manifold structure in graph embeddings
• Selecting the independent coordinates of manifolds with large aspect ratios