AI 中文总结
本研究通过统计决策理论和Fisher信息刻画稀疏随机块模型中的Kesten-Stigum阈值及信息-计算间隙，揭示低度规则与指数时间规则在阈值以下的性能差异，并验证置信传播和EM步骤的行为，实验支持理论预测。
AI 中文摘要
我们通过统计决策理论和Fisher信息研究具有$q$个社区、平均度$d$和信号强度$\lambda$的稀疏对称随机块模型中的社区恢复问题，并获得Kesten-Stigum阈值$d\lambda^2=1$及其以下信息-计算间隙的三个刻画。首先，在每个社区规模分布上，任何在平均和顶点重标定下封闭的规则类的极小极大风险等于其在均匀先验下的贝叶斯风险；后验均值是唯一的贝叶斯规则且是可容许的，并且$D$次多项式规则的贝叶斯风险是平凡风险乘以$1-\mathrm{Corr}_D^2$。结合已知的低度和信息论结果，这给出了间隙作为最坏情况陈述：对于$q\ge 5$，在阈值以下存在一个窗口，其中没有低度规则渐近地击败平凡风险，而指数时间规则在概率为$1-o(1)$的标记集合上确实击败平凡风险。其次，由环计数携带的关于$\lambda$的Fisher信息是一个级数，其项为$k(d\lambda^2)^k$阶，当且仅当$d\lambda^2<1$时收敛；在阈值以下，每个基于环的无偏估计器对$\lambda^k$的相对误差保持高于一个显式常数，并且每个环计数测试的成功概率被限制在小于1。第三，置信传播在其无信息不动点处的导数每次迭代将随机扰动乘以$|\lambda|\sqrt{d}$，并且在该处采取的一个EM步骤使$\lambda$保持不变。信噪比计算恢复了Chin等人针对$q=n^\chi$个社区的条件$d\lambda^{1/\chi}>1$，并将个性化PageRank识别为具有次优权重的游走计数。在多达$3\times 10^5$个顶点的网络上的实验证实了$q=2$的阈值、$q=5$的困难窗口以及多社区缩放。
英文摘要
We study community recovery in the sparse symmetric stochastic block model with $q$ communities, average degree $d$ and signal strength $λ$ through statistical decision theory and Fisher information, and obtain three characterizations of the Kesten-Stigum threshold $dλ^2=1$ and of the information-computation gap below it. First, on each community-size profile the minimax risk of any class of rules closed under averaging and vertex relabeling equals its Bayes risk under the uniform prior; the posterior mean is the unique Bayes rule and is admissible, and the Bayes risk of degree-$D$ polynomial rules is the trivial risk times $1-\mathrm{Corr}_D^2$. Combined with known low-degree and information-theoretic results, this gives the gap as a worst-case statement: for $q\ge 5$ there is a window below the threshold in which no low-degree rule beats the trivial risk asymptotically, while an exponential-time rule does on a set of labelings of probability $1-o(1)$. Second, the Fisher information about $λ$ carried by cycle counts is a series with terms of order $k(dλ^2)^k$, convergent exactly when $dλ^2<1$; below the threshold the relative error of every unbiased cycle-based estimator of $λ^k$ stays above an explicit constant, and every cycle-count test has success probability bounded below one. Third, the derivative of belief propagation at its uninformative fixed point multiplies a random perturbation by $|λ|\sqrt{d}$ per iteration, and one EM step taken there leaves $λ$ unchanged. A signal-to-noise computation recovers the condition $dλ^{1/χ}>1$ of Chin et al. for $q=n^χ$ communities and identifies personalized PageRank as a walk count with suboptimal weights. Experiments on networks with up to $3\times 10^5$ vertices confirm the threshold for $q=2$, the hard window for $q=5$, and the many-community scaling.
Comments36 pages, 4 figures, 6 tables
