arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.01871math.STcs.LGstat.TH
收藏

图子和随机块模型的非平凡估计何时可能?

When is Nontrivial Estimation Possible for Graphons and Stochastic Block Models?

Audra McMillan, Adam Smith

摘要:

块图子(也称为随机块模型)是一类重要且广泛研究的随机网络模型。我们提供了一个下界的准确性估计块图子大量的块。我们表明,只给的数量$k$的块和上界$ρ$的值(连接概率)的graphon,每个估计引起的错误至少在$\min(ρ, \sqrt{ρk^2/n^2})$的顺序在$δ_2$度量与恒定的概率,在最坏的情况下,在graphons。特别是,我们的界限排除了任何非平凡的估计(即,$δ_2$误差大大小于$ρ$)时,$k\geq n\sqrtρ$。结合以前的上界和下界,我们的结果特征,对数项,极小极大的准确性的graphon估计的$δ_2$度量。Klopp,Tsybakov和Verzelen(2016)独立获得了与我们相似的下界。

英文摘要:

Block graphons (also called stochastic block models) are an important and widely-studied class of models for random networks. We provide a lower bound on the accuracy of estimators for block graphons with a large number of blocks. We show that, given only the number $k$ of blocks and an upper bound $ρ$ on the values (connection probabilities) of the graphon, every estimator incurs error at least on the order of $\min(ρ, \sqrt{ρk^2/n^2})$ in the $δ_2$ metric with constant probability, in the worst case over graphons. In particular, our bound rules out any nontrivial estimation (that is, with $δ_2$ error substantially less than $ρ$) when $k\geq n\sqrtρ$. Combined with previous upper and lower bounds, our results characterize, up to logarithmic terms, the minimax accuracy of graphon estimation in the $δ_2$ metric. A similar lower bound to ours was obtained independently by Klopp, Tsybakov and Verzelen (2016).

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。

↑