Global Versus Local Methods in Nonlinear Dimensionality Reduction

Vin D. Silva, Joshua B. Tenenbaum

Advances in Neural Information Processing Systems 15 (NIPS 2002)

Recently proposed algorithms for nonlinear dimensionality reduction fall broadly into two categories which have different advantages and disad- vantages: global (Isomap [1]), and local (Locally Linear Embedding [2], Laplacian Eigenmaps [3]). We present two variants of Isomap which combine the advantages of the global approach with what have previ- ously been exclusive advantages of local methods: computational spar- sity and the ability to invert conformal maps.