Spectral Detection in the Censored Block Model
arXiv:1502.00163 · doi:10.1109/ISIT.2015.7282642
Abstract
We consider the problem of partially recovering hidden binary variables from the observation of (few) censored edge weights, a problem with applications in community detection, correlation clustering and synchronization. We describe two spectral algorithms for this task based on the non-backtracking and the Bethe Hessian operators. These algorithms are shown to be asymptotically optimal for the partial recovery problem, in that they detect the hidden assignment as soon as it is information theoretically possible to do so.
arXiv commentISIT 2015
References in corpus (5)
- Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications
- Spectral redemption: clustering sparse networks
- Hiding Quiet Solutions in Random Constraint Satisfaction Problems
- The high temperature region of the Viana-Bray diluted spin glass model
- Spectral density of the non-backtracking operator