Phase transitions for detecting latent geometry in random graphs
Phase transitions for detecting latent geometry in random graphs
复制标题
用于检测随机图中潜在几何形状的相变
DOI:
10.1007/s00440-020-00998-3
复制
发表时间:
2020
影响因子:
2
通讯作者:
Nagaraj, Dheeraj
中科院分区:
文献类型:
--
作者:
Brennan, Matthew;Bresler, Guy;Nagaraj, Dheeraj
Random graphs with latent geometric structure are popular models of social and biological networks, with applications ranging from network user profiling to circuit design. These graphs are also of purely theoretical interest within computer science, probability and statistics. A fundamental initial question regarding these models is: when are these random graphs affected by their latent geometry and when are they indistinguishable from simpler models without latent structure, such as the Erdős–Rényi graph? We address this question for two of the most well-studied models of random graphs with latent geometry—the random intersection and random geometric graph. Our results are as follows: (a) The random intersection graph is defined by samplingnrandom setsby including each element of a set of sizedin eachindependently with probability, and including the edgeif. We prove that the random intersection graph converges in total variation to an Erdős–Rényi graph if, and does not if, for both dense and sparse edge densitiesp. This resolves an open problem in Fill et al. (Random Struct Algorithms 16(2):156–176, 2000), Rybarczyk (Random Struct Algorithms 38(1–2):205–234, 2011) and Kim et al. (Random Struct Algorithms 52(4):662–679, 2018). The same result was obtained simultaneously and independently by Bubeck et al. (When random intersection graphs lose geometry. Manuscript, 2019). (b) We strengthen the preceding argument to show that the matrix of random intersection sizesconverges in total variation to a symmetric matrix with independent Poisson entries. This yields the first total variation convergence result for-random intersection graphs, where the edgeis included if. More precisely, our results imply that, ifpis bounded away from 1, then the-random intersection graph with edge densitypconverges toif. (c) The random geometric graph onis defined by samplinguniformly at random fromand including the edgeif. A result of Bubeck et al. (Random Struct Algorithms 49:503–532, 2016) showed that this model converges toin total variation, wherepis chosen so that the models have matching edge densities, as long as. It was conjectured in Bubeck et al. (2016) that this threshold decreases drastically forpsmall. We make the first progress towards this conjecture by showing convergence if. Our proofs are a hybrid of combinatorial arguments, direct couplings and applications of information inequalities. Previous upper bounds on the total variation distance between random graphs with latent geometry andhave typically not been both combinatorial and information-theoretic, while this interplay is essential to the sharpness of our bounds.
登录
查看更多内容
DOI:
--
发表时间:
2020-05
期刊:
--
影响因子:
--
作者:
Matthew Brennan;Guy Bresler
通讯作者:
Matthew Brennan;Guy Bresler
DOI:
--
发表时间:
2008
期刊:
2008 IEEE International Symposium on Information Theory
影响因子:
--
作者:
Osman Yağan;A. Makowski
通讯作者:
A. Makowski
影响因子:
--
作者:
Ronen Eldan;Dan Mikulincer
通讯作者:
Dan Mikulincer
DOI:
--
发表时间:
2015
期刊:
影响因子:
--
作者:
Will Perkins
通讯作者:
Will Perkins
DOI:
--
发表时间:
2009
期刊:
Random Struct. Algorithms
影响因子:
--
作者:
K. Rybarczyk
通讯作者:
K. Rybarczyk