
Information Limits for Recovering a Hidden Community
We study the problem of recovering a hidden community of cardinality K f...
read it

Achieving Exact Cluster Recovery Threshold via Semidefinite Programming
The binary symmetric stochastic block model deals with a random graph of...
read it

Achieving Exact Cluster Recovery Threshold via Semidefinite Programming: Extensions
Resolving a conjecture of Abbe, Bandeira and Hall, the authors have rece...
read it

Multisection in the Stochastic Block Model using Semidefinite Programming
We consider the problem of identifying underlying communitylike structu...
read it

On semidefinite relaxations for the block model
The stochastic block model (SBM) is a popular tool for community detecti...
read it

Exact Recovery of Community Detection in kpartite Graph Models
We study the vertex classification problem on a graph in which the verti...
read it

Open problem: Tightness of maximum likelihood semidefinite relaxations
We have observed an interesting, yet unexplained, phenomenon: Semidefini...
read it
Semidefinite Programs for Exact Recovery of a Hidden Community
We study a semidefinite programming (SDP) relaxation of the maximum likelihood estimation for exactly recovering a hidden community of cardinality K from an n × n symmetric data matrix A, where for distinct indices i,j, A_ij∼ P if i, j are both in the community and A_ij∼ Q otherwise, for two known probability distributions P and Q. We identify a sufficient condition and a necessary condition for the success of SDP for the general model. For both the Bernoulli case (P= Bern(p) and Q= Bern(q) with p>q) and the Gaussian case (P=N(μ,1) and Q=N(0,1) with μ>0), which correspond to the problem of planted dense subgraph recovery and submatrix localization respectively, the general results lead to the following findings: (1) If K=ω( n / n), SDP attains the informationtheoretic recovery limits with sharp constants; (2) If K=Θ(n/ n), SDP is orderwise optimal, but strictly suboptimal by a constant factor; (3) If K=o(n/ n) and K →∞, SDP is orderwise suboptimal. The same critical scaling for K is found to hold, up to constant factors, for the performance of SDP on the stochastic block model of n vertices partitioned into multiple communities of equal size K. A key ingredient in the proof of the necessary condition is a construction of a primal feasible solution based on random perturbation of the true cluster matrix.
READ FULL TEXT
Comments
There are no comments yet.