Central Limit Theorems and Network-Free Inference for Heterogeneous Spatial Autoregressions on Sparse Graphons

Abstract

Network dependence is widely regarded as a fundamental obstacle to inference: outcomes linked through a graph are not independent, the graph is rarely observed in full, and models for how dependence propagates are easily misspecified. We show that for a broad class of responses generated through a random network, the obstacle is smaller than it appears. We study a heterogeneous spatial autoregression on a sparse graphon, in which each node's response is a weighted average of its neighbors' responses with a node-specific, nonparametric coefficient plus a node-specific input, and we prove that sample means and smooth functions of vector means are asymptotically Gaussian down to average degree nearly logarithmic in the population size, allowing unbounded graphons with hubs and heavy-tailed inputs. The limiting variance interpolates exactly between two regimes according to the sampling fraction. When the observed nodes are a vanishing fraction of the population, the variance is the marginal variance of the response, the ordinary sample variance is consistent, and the usual t-interval is valid with no knowledge of the network. The proof averages over the graph rather than conditioning on it, isolating the behavior of the response through an exact identity for resolvents of Markov kernels and controlling the network noise by an Efron-Stein inequality; neither step requires the walk-by-walk covariance bounds of fixed-network analyses. Consequences for regression with node-level and network-derived covariates are derived.

Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport
Kim Jakwang, Kwon Dohyun
arXiv4 Sep 2026PreprintCC BY 4.0Full textProbability StatisticsarXiv
Spectral Analysis of Gram Matrices with Missing at Random Observations: Convergence, Central Limit Theorems, and Applications in Statistical Inference
Huiqin Li, Guangming Pan, Yanqing Yin +1
arXiv2 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
Global central limit theorems for Markov chains
Christophe Cuny, Michael Lin
Stochastic Processes and their Applications2 Oct 2026Peer-reviewedCC BY 4.0Full text1 citedMathematical physicsHAL
Global Central Limit Theorems for Markov chains with normal transition operator
Christophe Cuny, Michael Lin
HAL30 Sep 2026PreprintCC BY-NC-ND 4.0Full textProbabilityHALarXiv
Functional central limit theorems for Laguerre tessellations
Chinmoy Bhattacharjee, Anna Gusakova, Christian Hirsch
arXiv5 Oct 2026PreprintCC BY 4.0Full textProbabilityarXiv

Cite

BibTeX RIS

BibTeX

@misc{li2026central,
  title = {{Central Limit Theorems and Network-Free Inference for Heterogeneous Spatial Autoregressions on Sparse Graphons}},
  author = {Wei Li and Robert Lunde},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.40630},
  eprint = {2610.40630},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.40630},
}

RIS

TY  - UNPB
TI  - Central Limit Theorems and Network-Free Inference for Heterogeneous Spatial Autoregressions on Sparse Graphons
AU  - Wei Li
AU  - Robert Lunde
PY  - 2026
DA  - 2026/10/29
PB  - arXiv
DO  - 10.48550/arxiv.2610.40630
UR  - https://arxiv.org/abs/2610.40630
AB  - Network dependence is widely regarded as a fundamental obstacle to inference: outcomes linked through a graph are not independent, the graph is rarely observed in full, and models for how dependence propagates are easily misspecified. We show that for a broad class of responses generated through a random network, the obstacle is smaller than it appears. We study a heterogeneous spatial autoregression on a sparse graphon, in which each node's response is a weighted average of its neighbors' responses with a node-specific, nonparametric coefficient plus a node-specific input, and we prove that sample means and smooth functions of vector means are asymptotically Gaussian down to average degree nearly logarithmic in the population size, allowing unbounded graphons with hubs and heavy-tailed inputs. The limiting variance interpolates exactly between two regimes according to the sampling fraction. When the observed nodes are a vanishing fraction of the population, the variance is the marginal variance of the response, the ordinary sample variance is consistent, and the usual t-interval is valid with no knowledge of the network. The proof averages over the graph rather than conditioning on it, isolating the behavior of the response through an exact identity for resolvents of Markov kernels and controlling the network noise by an Efron-Stein inequality; neither step requires the walk-by-walk covariance bounds of fixed-network analyses. Consequences for regression with node-level and network-derived covariates are derived.
ER  -

Abstract

Related

Cite