Essentially tight thresholds for detectability of latent geometry in bipartite Gaussian RGGs under Bern(q) masked edges are determined for fixed p, ruling out computational-statistical gaps via a new Fourier-analytic framework.
High-dimensional random geometric graphs and their clique number
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.PR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Information-Theoretic Thresholds for Bipartite Latent-Space Graphs under Noisy Observations
Essentially tight thresholds for detectability of latent geometry in bipartite Gaussian RGGs under Bern(q) masked edges are determined for fixed p, ruling out computational-statistical gaps via a new Fourier-analytic framework.