arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.03362math.PRcs.SImath.COmath.STstat.TH
收藏

随机块模型的精确相变与树上的重构

Exact Phase Transitions for Stochastic Block Models and Reconstruction on Trees

Elchanan Mossel, Allan Sly, Youngtak Sohn

AI总结:

该研究通过树与图过程的新耦合方法及树上广播过程的精细分析,严格论证了随机块模型中q=3、q=4社区情形的Kesten-Stigum界相关猜想,明确了不同社区数量下的计算-统计差距与界的紧性特征。

摘要:

本文继续严格论证Decelle、Krzakala、Moore、Zdeborová(2011)在统计物理领域开创性工作中提出的关于块模型的预测,重点针对q=3和q=4个社区的情形。我们证明,当平均度高于某个常数时,q=3和q=4的情形不存在计算-统计差距,论证依据是在Kesten-Stigum界以下,信息论层面无法实现检测。该证明的基础是:对于Galton-Watson树(高尔顿-沃森树)上的广播过程,当平均度足够大时,q=3和q=4的情形下重构是不可能的。这一结果改进了Sly(2009)的结论,后者针对q=3的正则树证明了类似结果。我们对临界情形q=4的分析给出了详细的图景,表明反铁磁情形下Kesten-Stigum界的紧性取决于树的平均度。我们还证明,当q≥5时,Kesten-Stigum界并非紧的。我们的结果证明了Decelle、Krzakala、Moore、Zdeborová(2011)、Moore(2017)、Abbe与Sandon(2018)以及Ricci-Tersenghi、Semerjian与Zdeborová(2019)提出的猜想。我们的证明基于一种新的树过程与图过程的通用耦合方法,以及对树上广播过程的精细化分析。

英文摘要:

In this paper we continue to rigorously establish the predictions in ground breaking work in statistical physics by Decelle, Krzakala, Moore, Zdeborová (2011) regarding the block model, in particular in the case of $q=3$ and $q=4$ communities. We prove that for $q=3$ and $q=4$ there is no computational-statistical gap if the average degree is above some constant by showing it is information theoretically impossible to detect below the Kesten-Stigum bound. The proof is based on showing that for the broadcast process on Galton-Watson trees, reconstruction is impossible for $q=3$ and $q=4$ if the average degree is sufficiently large. This improves on the result of Sly (2009), who proved similar results for regular trees for $q=3$. Our analysis of the critical case $q=4$ provides a detailed picture showing that the tightness of the Kesten-Stigum bound in the antiferromagnetic case depends on the average degree of the tree. We also prove that for $q\geq 5$, the Kestin-Stigum bound is not sharp. Our results prove conjectures of Decelle, Krzakala, Moore, Zdeborová (2011), Moore (2017), Abbe and Sandon (2018) and Ricci-Tersenghi, Semerjian, and Zdeborová (2019). Our proofs are based on a new general coupling of the tree and graph processes and on a refined analysis of the broadcast process on the tree.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑