Nonlinear dimensionality reduction methods often rely on the nearest-neighbors graph to extract low-dimensional embeddings that reliably capture the underlying structure of high-d...
For many pattern recognition methods, high recognition accuracy is obtained at very high expense of computational cost. In this paper, a new algorithm that reduces the computation...
Fang Sun, Shinichiro Omachi, Nei Kato, Hirotomo As...
Many unsupervised algorithms for nonlinear dimensionality reduction, such as locally linear embedding (LLE) and Laplacian eigenmaps, are derived from the spectral decompositions o...
In the last decades, a large family of algorithms supervised or unsupervised; stemming from statistic or geometry theory have been proposed to provide different solutions to the p...
We study the problem of projecting high-dimensional tensor data on an unspecified Riemannian manifold onto some lower dimensional subspace1 without much distorting the pairwise geo...