arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.00833stat.MEstat.ML
收藏

非齐次随机图的双样本假设检验

Two-sample Hypothesis Testing for Inhomogeneous Random Graphs

Debarghya Ghoshdastidar, Maurilio Gutzeit, Alexandra Carpentier, Ulrike von Luxburg

摘要:

网络的研究导致了广泛的高维推理问题。在许多实际应用中,人们需要从一个或几个大型稀疏网络中进行推理。本文研究在这个高维制度,其中的目标是测试两个人口的非齐次随机图定义在同一组$n$顶点之间的图的假设检验。每个群体的大小$m$比$n$小得多,甚至可以是小到1的常数。在这种情况下的关键问题是问题是否是小$m$可解的。我们从极大极小检验的角度来回答这个问题。设$P,Q$为两个稀疏非齐次随机图模型的总体邻接,$d$为适当定义的距离函数.给定一个人口的$m$图从每个模型中,我们得到的问题测试$P=Q$对$d(P,Q)>ρ$的极大极小分离率。我们观察到,如果$m$是小的,那么极小极大分离是太大的$d$,包括相应的分布之间的总变异距离的一些流行的选择。这意味着,在$d$中被广泛分离的一些模型不能被区分为小的$m$,因此,在这些情况下,测试问题通常是不可解决的。我们还表明,如果$m>1$,那么极大极小分离是相对较小的,如果$d$是Frobenius范数或运营商范数之间的距离$P$和$Q$。对于$m=1$,只有后一个距离提供小的极大极小分离。因此,对于这些距离,该问题对于小的$m$是可解的。我们还提出了近最佳的两个样本测试在这两种情况下,测试是自适应的稀疏度水平的图形。

英文摘要:

The study of networks leads to a wide range of high dimensional inference problems. In many practical applications, one needs to draw inference from one or few large sparse networks. The present paper studies hypothesis testing of graphs in this high-dimensional regime, where the goal is to test between two populations of inhomogeneous random graphs defined on the same set of $n$ vertices. The size of each population $m$ is much smaller than $n$, and can even be a constant as small as 1. The critical question in this context is whether the problem is solvable for small $m$. We answer this question from a minimax testing perspective. Let $P,Q$ be the population adjacencies of two sparse inhomogeneous random graph models, and $d$ be a suitably defined distance function. Given a population of $m$ graphs from each model, we derive minimax separation rates for the problem of testing $P=Q$ against $d(P,Q)>ρ$. We observe that if $m$ is small, then the minimax separation is too large for some popular choices of $d$, including total variation distance between corresponding distributions. This implies that some models that are widely separated in $d$ cannot be distinguished for small $m$, and hence, the testing problem is generally not solvable in these cases. We also show that if $m>1$, then the minimax separation is relatively small if $d$ is the Frobenius norm or operator norm distance between $P$ and $Q$. For $m=1$, only the latter distance provides small minimax separation. Thus, for these distances, the problem is solvable for small $m$. We also present near-optimal two-sample tests in both cases, where tests are adaptive with respect to sparsity level of the graphs.

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。

↑