Achieving the Bayes Error Rate in Synchronization and Block Models by SDP, Robustly

TL;DR

This paper demonstrates that semidefinite programming (SDP) achieves the optimal error rate and exact recovery thresholds in synchronization and block models, and remains robust against adversarial modifications.

Contribution

It proves that SDP is Bayes optimal and robust for clustering in multiple random graph models, providing a unified primal-dual analysis framework.

Findings

SDP achieves error rate \\exp[-(1-o(1))\\bar{n} I^*] in models

SDP matches lower bounds, proving Bayes optimality

SDP remains effective under semi-random adversarial modifications

Abstract

We study the statistical performance of semidefinite programming (SDP) relaxations for clustering under random graph models. Under the $\mathbb{Z}_{2}$ Synchronization model, Censored Block Model and Stochastic Block Model, we show that SDP achieves an error rate of the form \[ \exp\Big[-\big(1-o(1)\big)\bar{n} I^* \Big]. \] Here $\bar{n}$ is an appropriate multiple of the number of nodes and $I^*$ is an information-theoretic measure of the signal-to-noise ratio. We provide matching lower bounds on the Bayes error for each model and therefore demonstrate that the SDP approach is Bayes optimal. As a corollary, our results imply that SDP achieves the optimal exact recovery threshold under each model. Furthermore, we show that SDP is robust: the above bound remains valid under semirandom versions of the models in which the observed graph is modified by a monotone adversary. Our proof is based on a novel primal-dual analysis of SDP under a unified framework for all three models, and the analysis shows that SDP tightly approximates a joint majority voting procedure.