Answers are grounded in this paper and cite their sources.
This analysis uncovers the link between SDP and MLE in the high-noise regime, suggesting significant error patterns. The Burer-Monteiro factorization also shows exponential deviations in these conditions.
We study the difference between the maximum likelihood estimation (MLE) and its semi-definite programming (SDP) relaxation for the phase synchronization problem, where n latent phases are estimated based on pairwise observations corrupted by Gaussian noise at a level $σ$. While previous studies have established that SDP coincides with the MLE when σ √n / log n, the behavior in the high-noise regime σ √n / log n remains unclear. We address this gap by quantifying the deviation between the SDP and the MLE in the high-noise regime as exp(-c n/σ²), indicating an exponentially small discrepancy. In fact, we establish more general results for the Burer-Monteiro (BM) factorization that covers the SDP as a special case: it has the exponentially small deviation from the MLE in the high-noise regime and coincides with the MLE when $σ$ is small. To obtain our results, we develop a refined entrywise analysis of the MLE that is beyond the existing _∞ analysis in literature.
No takes yet. Share an insight, caveat, or question.
Anderson Ye Zhang (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: