A decomposition framework for simple and composite perturbations in normalized adjacency matrices improves the allowable number of communities to K=o(n^{1/6}) for largest-eigenvalue tests and completes the asymptotic normality proof for linear spectral statistics in SBMs.
(2018).High-Dimensional Probability: An Introduction with Applications in Data Sci- ence.Cambridge Series in Statistical and Probabilistic Mathematics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Simple to Composite Perturbations: A Unified Decomposition Framework for Stochastic Block Models
A decomposition framework for simple and composite perturbations in normalized adjacency matrices improves the allowable number of communities to K=o(n^{1/6}) for largest-eigenvalue tests and completes the asymptotic normality proof for linear spectral statistics in SBMs.