Distance Preserving Embeddings for General n-Dimensional Manifolds


Nakul Verma ;
Proceedings of the 25th Annual Conference on Learning Theory, PMLR 23:32.1-32.28, 2012.


Low dimensional embeddings of manifold data have gained popularity in the last decade. However, a systematic finite sample analysis of manifold embedding algorithms largely eludes researchers. Here we present two algorithms that, given access to just the samples, embed the underlying n- dimensional manifold into R^d (where d only depends on some key manifold properties such as its intrinsic dimension, volume and curvature) and \emphguarantee to approximately preserve all interpoint geodesic distances.

Related Material