New bounds for circulant Johnson-Lindenstrauss embeddings

From MaRDI portal
Publication:471965

DOI10.4310/CMS.2014.V12.N4.A5zbMATH Open1366.15031arXiv1308.6339MaRDI QIDQ471965FDOQ471965


Authors: Hui Zhang, Li-zhi Cheng Edit this on Wikidata


Publication date: 18 November 2014

Published in: Communications in Mathematical Sciences (Search for Journal in Brave)

Abstract: This paper analyzes circulant Johnson-Lindenstrauss (JL) embeddings which, as an important class of structured random JL embeddings, are formed by randomizing the column signs of a circulant matrix generated by a random vector. With the help of recent decoupling techniques and matrix-valued Bernstein inequalities, we obtain a new bound k=O(epsilon2log(1+delta)(n)) for Gaussian circulant JL embeddings. Moreover, by using the Laplace transform technique (also called Bernstein's trick), we extend the result to subgaussian case. The bounds in this paper offer a small improvement over the current best bounds for Gaussian circulant JL embeddings for certain parameter regimes and are derived using more direct methods.


Full work available at URL: https://arxiv.org/abs/1308.6339




Recommendations





Cited In (7)





This page was built for publication: New bounds for circulant Johnson-Lindenstrauss embeddings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q471965)