Optimal Distributed Composite Testing in High-dimensional Gaussian Models with 1-bit Communication

Szabo, Botond; Vuursteen, Lasse; Van Zanten, Harry Van

doi:10.1109/TIT.2022.3150599

Optimal Distributed Composite Testing in High-dimensional Gaussian Models with 1-bit Communication

Journal article (2022)

Authors

Botond Szabo Università Bocconi

Lasse Vuursteen Statistics

Harry Van Van Zanten Vrije Universiteit Amsterdam

Research Group

Statistics

DOI: https://doi.org/10.1109/TIT.2022.3150599

Testing Hypothesis testing Distributed algorithms Gaussian noise Minimax lower bounds

To reference this document use:

http://resolver.tudelft.nl/uuid:e221a329-531b-42df-b309-c8f8b3de23b1

More Info

expand_more

Published Date

2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Research Group

Statistics

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.

Files

Optimal_Distributed_Composite_... (pdf)

(pdf | 1.61 Mb)

License info not available

Download not available

Optimal_Distributed_Composite_... (pdf)

(pdf | 0.99 Mb)

- Embargo expired in 01-07-2023

License info not available