多簇随机块模型中的检测:可扩展性证明、非循环BP和信息计算间隙
Detection in the stochastic block model with multiple clusters: proof of the achievability conjectures, acyclic BP, and the information-computation gap
摘要:
在一篇开创了随机块模型现代研究的论文中,Decelle等人,在Mossel等人的支持下,做出了如下推测:用$k$表示平衡社区的数量,$a/n$表示连接社区内部和$b/n$之间的概率,并设置$\mathrm{SNR}=(a-b)^2/(k(a+(k-1)b)$ ;对于任何$k \geq 2$,只要$\mathrm{SNR}>1$(KS阈值),就可以有效地检测社区,而对于$k\geq 4$,对于某些$\mathrm{SNR}<1$,理论上可以检测社区。马苏利埃、莫塞尔等人\ Bordenave et al.成功地证明了KS阈值对于$k=2$是有效地可实现的,而Mossel等人证明了它不能交叉信息理论上$k=2$。上述猜想对于$k \geq 3$仍然是开放的。本文证明了这一猜想,进一步扩展的有效检测非对称SBMs的检测和KS阈值的广义概念。对于有效的部分,线性化的非循环的信念传播(ABP)算法的开发和证明,以检测社区的任何$k$下降到KS阈值的时间$O(n \log n)$。要实现这一点,需要在存在循环的情况下显示ABP的最优性,这对消息传递算法来说是一个挑战。本文进一步将ABP与具有广义阶非回溯算子的幂迭代方法相连接,形式化了消息传递和谱方法之间的相互作用。对于信息理论(IT)的一部分,一个非有效的算法采样一个典型的聚类分解的KS阈值在$k=4$。在某些情况下,新出现的差距被证明是大的,如果$a=0$,KS阈值读取$b \gtrsim k^2$,而IT绑定读取$b \gtrsim k \ln(k)$,使SBM信息计算差距的一个很好的研究案例。
英文摘要:
In a paper that initiated the modern study of the stochastic block model, Decelle et al., backed by Mossel et al., made the following conjecture: Denote by $k$ the number of balanced communities, $a/n$ the probability of connecting inside communities and $b/n$ across, and set $\mathrm{SNR}=(a-b)^2/(k(a+(k-1)b)$; for any $k \geq 2$, it is possible to detect communities efficiently whenever $\mathrm{SNR}>1$ (the KS threshold), whereas for $k\geq 4$, it is possible to detect communities information-theoretically for some $\mathrm{SNR}<1$. Massoulié, Mossel et al.\ and Bordenave et al.\ succeeded in proving that the KS threshold is efficiently achievable for $k=2$, while Mossel et al.\ proved that it cannot be crossed information-theoretically for $k=2$. The above conjecture remained open for $k \geq 3$. This paper proves this conjecture, further extending the efficient detection to non-symmetrical SBMs with a generalized notion of detection and KS threshold. For the efficient part, a linearized acyclic belief propagation (ABP) algorithm is developed and proved to detect communities for any $k$ down to the KS threshold in time $O(n \log n)$. Achieving this requires showing optimality of ABP in the presence of cycles, a challenge for message passing algorithms. The paper further connects ABP to a power iteration method with a nonbacktracking operator of generalized order, formalizing the interplay between message passing and spectral methods. For the information-theoretic (IT) part, a non-efficient algorithm sampling a typical clustering is shown to break down the KS threshold at $k=4$. The emerging gap is shown to be large in some cases; if $a=0$, the KS threshold reads $b \gtrsim k^2$ whereas the IT bound reads $b \gtrsim k \ln(k)$, making the SBM a good study-case for information-computation gaps.
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。