Mahmoudi, MonaVandergheynst, PierreSorci, Matteo2008-01-212008-01-212008-01-21200810.1109/ICIP.2008.4712136https://infoscience.epfl.ch/handle/20.500.14299/16371In this paper, we focus on the use of random projections as a dimensionality reduction tool for sampled manifolds in high-dimensional Euclidean spaces. We show that geodesic paths approximations from nearest neighbors Euclidean distances are well-preserved by Gaussian projections and we characterize the distribution of geodesic lengths in the reduced dimensional point cloud. A stylized application to a real-world data set of human faces is presented to validate our theoretical findings.dimensionality reductionmanifold learningrandom projectionsLTS2LTS5text::conference output::conference proceedings::conference paper