Random Embeddings with Optimal Accuracy

arXiv2101.00029MaRDI QIDQ6357345FDOQ6357345

Authors: Maciej Skórski 

Publication date: 31 December 2020

Abstract: This work constructs Jonson-Lindenstrauss embeddings with best accuracy, as measured by variance, mean-squared error and exponential concentration of the length distortion. Lower bounds for any data and embedding dimensions are determined, and accompanied by matching and efficiently samplable constructions (built on orthogonal matrices). Novel techniques: a unit sphere parametrization, the use of singular-value latent variables and Schur-convexity are of independent interest.

This page was built for publication: Random Embeddings with Optimal Accuracy

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6357345)