Toward a unified theory of sparse dimensionality reduction in Euclidean space

Let be a sparse Johnson-Lindenstrauss transform (Kane and Nelson in J ACM 61(1):4, 2014) with s non-zeroes per column. For a subset T of the unit sphere, given, we study settings for m, s required to ensure i.e. so that preserves the norm of every simultaneously and multiplicatively up to . We introduce a new complexity parameter, which depends on the geometry of T, and show that it suffices to choose s and m such that this parameter is small. Our result is a sparse analog of Gordon's theorem, which was concerned with a dense having i.i.d. Gaussian entries. We qualitatively unify several results related to the Johnson-Lindenstrauss lemma, subspace embeddings, and Fourier-based restricted isometries. Our work also implies new results in using the sparse Johnson-Lindenstrauss transform in numerical linear algebra, classical and model-based compressed sensing, manifold learning, and constrained least squares problems such as the Lasso.