← 研踪 PaperTrailarXiv:2611.23547 · v1
Bounded-Order Non-Identifiability in Latent Structure Block Models: The Fiber in Closed Form
首次提交 2026-11-18 05:53
版本更新 2026-11-18 05:53
雷达观测 2026-11-19 19:08
摘要
A graphon is determined by all of its homomorphism densities, but motif-based methods use finitely many. We compute exactly what that truncation costs in a natural family: latent structure block models whose positions lie on rays, equivalently degree-corrected block models of rank two. For a given radial law, the configurations that agree on every graph with fewer than vertices form a one-dimensional fiber, which we give in closed form with explicit endpoints; the friendship graph is its unique edge-minimal separator, so no fixed motif order serves every . The separating signal is suppressed by a factor of at most , where is the mean squared slope, about at : detecting it from motif counts would take about nodes in a single graph, at any edge density. The information is nonetheless in the graph; the fiber belongs to the statistic, not the model. Common spectral pipelines, which count no motifs, still slide along the fiber by more than a third of its length at ordinary densities, with confidence regions that almost never contain the truth, while model-based fits of the same embedding do not. We give practitioners four checks: whether a fit is at risk, what to run instead, why a confidence interval will not warn, and how wide the remaining ambiguity is.
作者备注:Submitted to AISTATS 2027
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-18 05:53 · 最新观测版本
Bounded-Order Non-Identifiability in Latent Structure Block Models: The Fiber in Closed Form
A graphon is determined by all of its homomorphism densities, but motif-based methods use finitely many. We compute exactly what that truncation costs in a natural family: latent structure block models whose positions lie on rays, equivalently degree-corrected block models of rank two. For a given radial law, the configurations that agree on every graph with fewer than vertices form a one-dimensional fiber, which we give in closed form with explicit endpoints; the friendship graph is its unique edge-minimal separator, so no fixed motif order serves every . The separating signal is suppressed by a factor of at most , where is the mean squared slope, about at : detecting it from motif counts would take about nodes in a single graph, at any edge density. The information is nonetheless in the graph; the fiber belongs to the statistic, not the model. Common spectral pipelines, which count no motifs, still slide along the fiber by more than a third of its length at ordinary densities, with confidence regions that almost never contain the truth, while model-based fits of the same embedding do not. We give practitioners four checks: whether a fit is at risk, what to run instead, why a confidence interval will not warn, and how wide the remaining ambiguity is.
查看此版本解读 →查看此版本原文 ↗