🤖 AI Summary
This study addresses the information-computation gap in community recovery within sparse stochastic block models, where the properties of the Kesten-Stigum threshold remain insufficiently characterized. By integrating statistical decision theory with Fisher information, this work proposes a triple characterization framework encompassing minimax risk equivalence, cycle-counting Fisher information convergence, and EM step-size invariance. Theoretical derivations are conducted using Bayesian risk, low-degree polynomial methods, and belief propagation algorithms. This research rigorously establishes the existence of the threshold for two communities (q=2) and identifies the hard phase window for five communities (q=5), elucidating generalization patterns for multi-community extensions. Furthermore, experiments on networks comprising up to 300,000 nodes validate the accuracy of these theoretical predictions.
📝 Abstract
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.