Sharp Signal Detection Under Ferromagnetic Ising Models
Statistics Theory
2021-10-07 v1 Probability
Statistics Theory
Abstract
In this paper we study the effect of dependence on detecting a class of structured signals in Ferromagnetic Ising models. Natural examples of our class include Ising Models on lattices, and Mean-Field type Ising Models such as dense Erd\H{o}s-R\'{e}nyi, and dense random regular graphs. Our results not only provide sharp constants of detection in each of these cases and thereby pinpoint the precise relationship of the detection problem with the underlying dependence, but also demonstrate how to be agnostic over the strength of dependence present in the respective models.
Keywords
Cite
@article{arxiv.2110.02949,
title = {Sharp Signal Detection Under Ferromagnetic Ising Models},
author = {Sohom Bhattacharya and Rajarshi Mukherjee and Gourab Ray},
journal= {arXiv preprint arXiv:2110.02949},
year = {2021}
}