Optimal distributed composite testing in high-dimensional Gaussian models with 1-bit communication
Information Theory
2022-02-28 v2 math.IT
Statistics Theory
Machine Learning
Statistics Theory
Abstract
In this paper we study the problem of signal detection in Gaussian noise in a distributed setting where the local machines in the star topology can communicate a single bit of information. We derive a lower bound on the Euclidian norm that the signal needs to have in order to be detectable. Moreover, we exhibit optimal distributed testing strategies that attain the lower bound.
Cite
@article{arxiv.2012.04957,
title = {Optimal distributed composite testing in high-dimensional Gaussian models with 1-bit communication},
author = {Botond Szabo and Lasse Vuursteen and Harry van Zanten},
journal= {arXiv preprint arXiv:2012.04957},
year = {2022}
}
Comments
33 pages, 2 figures. To appear in IEEE Transactions on Information Theory