Typology of phase transitions in Bayesian inference problems

TL;DR

This paper explores phase transitions in Bayesian inference problems like the stochastic block model, revealing complex phases including hybrid-hard regimes where inference is computationally easier than optimal, supported by cavity method analysis.

Contribution

It introduces a refined phase diagram for inference problems, identifying hybrid-hard phases and analyzing the tightness of the Kesten-Stigum bound across various models.

Findings

Hybrid-hard phases exist where inference is easier than the optimal.

Kesten-Stigum bound is tight in assortative SBM but not in disassortative cases.

Degree distribution influences the tightness of the KS bound in Potts models.

Abstract

Many inference problems, notably the stochastic block model (SBM) that generates a random graph with a hidden community structure, undergo phase transitions as a function of the signal-to-noise ratio, and can exhibit hard phases in which optimal inference is information-theoretically possible but computationally challenging. In this paper we refine this description by emphasizing the existence of more generic phase diagrams with a hybrid-hard phase in which it is computationally easy to reach a non-trivial inference accuracy, but computationally hard to match the information theoretically optimal one. We support this discussion by quantitative expansions of the functional cavity equations that describe inference problems on sparse graphs. These expansions shed light on the existence of hybrid-hard phases, for a large class of planted constraint satisfaction problems, and on the question of the tightness of the Kesten-Stigum (KS) bound for the associated tree reconstruction problem. Our results show that the instability of the trivial fixed point is not a generic evidence for the Bayes-optimality of the message passing algorithms. We clarify in particular the status of the symmetric SBM with 4 communities and of the tree reconstruction of the associated Potts model: in the assortative (ferromagnetic) case the KS bound is always tight, whereas in the disassortative (antiferromagnetic) case we exhibit an explicit criterion involving the degree distribution that separates a large degree regime where the KS bound is tight and a low degree regime where it is not. We also investigate the SBM with 2 communities of different sizes, a.k.a. the asymmetric Ising model, and describe quantitatively its computational gap as a function of its asymmetry, and a version of the SBM with 2 groups of communities. We complement this study with numerical simulations of the Belief Propagation algorithm.