Limits and Performances of Algorithms Based on Simulated Annealing in Solving Sparse Hard Inference Problems

The planted-coloring problem is a prototypical inference problem for which thresholds for Bayes-optimal algorithms, like belief propagation (BP), can be computed analytically. In this paper, we analyze the limits and performances of simulated annealing (SA), a Monte-Carlo-based algorithm that is more general and robust than BP, and thus of broader applicability. We show that SA is suboptimal in the recovery of the planted solution because it gets attracted by glassy states that, instead, do not influence the BP algorithm. At variance with previous conjectures, we propose an analytic estimation for the SA algorithmic threshold by comparing the spinodal point of the paramagnetic phase and the dynamical critical temperature. This is a fundamental connection between thermodynamical phase transitions and out-of-equilibrium behavior of Glauber dynamics. We also study an improved version of SA, called replicated SA (RSA), where several weakly coupled replicas are cooled down together. We show numerical evidence that the algorithmic threshold for the RSA coincides with the Bayes-optimal one. Finally, we develop an approximated analytical theory explaining the optimal performances of RSA and predicting the location of the transition toward the planted solution in the limit of a very large number of replicas. Our results for RSA support the idea that mismatching the parameters in the prior with respect to those of the generative model may produce an algorithm that is optimal and very robust.