Application of information-percolation method to reconstruction problems on graphs
arXiv:1806.04195
Abstract
In this paper we propose a method of proving impossibility results based on applying strong data-processing inequalities to estimate mutual information between sets of variables forming certain Markov random fields. The end result is that mutual information between two "far away" (as measured by the graph distance) variables is bounded by the probability of the existence of an open path in a bond-percolation problem on the same graph. Furthermore, stronger bounds can be obtained by establishing mutual information comparison results with an erasure model on the same graph, with erasure probabilities given by the contraction coefficients. As applications, we show that our method gives sharp threshold for partially recovering a rank-one perturbation of a random Gaussian matrix (spiked Wigner model), yields the best known upper bound on the noise level for group synchronization (obtained concurrently by Abbe and Boix), and establishes new impossibility result for community detection on the stochastic block model with communities.
References in corpus (6)
- Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula
- MMSE of probabilistic low-rank matrix estimation: Universality with respect to the output channel
- Mutual Information in Rank-One Matrix Estimation
- Comparison of Channels: Criteria for Domination by a Symmetric Channel
- Asymptotic Mutual Information for the Two-Groups Stochastic Block Model
- An Information-Percolation Bound for Spin Synchronization on General Graphs