A limit theorem for scaled eigenvectors of random dot product graphs

DOI10.1007/S13171-015-0071-XzbMATH Open1338.62061arXiv1305.7388OpenAlexW1531677314MaRDI QIDQ288255FDOQ288255

Daniel L. Sussman, David J. Marchette, Avanti Athreya, Vince Lyzinski, Minh Tang, Carey E. Priebe

Publication date: 25 May 2016

Published in: Sankhyā. Series A (Search for Journal in Brave)

Abstract: We prove a central limit theorem for the components of the largest eigenvectors of the adjacency matrix of a finite-dimensional random dot product graph whose true latent positions are unknown. In particular, we follow the methodology outlined in citet{sussman2012universally} to construct consistent estimates for the latent positions, and we show that the appropriately scaled differences between the estimated and true latent positions converge to a mixture of Gaussian random variables. As a corollary, we obtain a central limit theorem for the first eigenvector of the adjacency matrix of an Erd"os-Renyi random graph.

Full work available at URL: https://arxiv.org/abs/1305.7388

Recommendations

• Limit theorems for eigenvectors of the normalized Laplacian for random graphs
• Efficient Estimation for Random Dot Product Graphs via a One-Step Procedure
• Eigenvalues of stochastic blockmodel graphs and random graphs with low-rank edge probability matrices
• Statistical inference on random dot product graphs: a survey
• Sparse random graphs: eigenvalues and eigenvectors

zbMATH Keywords

model-based clusteringcentral limit theoremrandom dot product graph

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Random graphs (graph-theoretic aspects) (05C80) Central limit and other weak theorems (60F05)

Cites Work

• MCLUST: Software for model-based cluster analysis
• A nonparametric view of network models and Newman–Girvan and other modularities
• Spectral clustering and the high-dimensional stochastic blockmodel
• A Survey of Statistical Network Models
• Title not available (Why is that?)
• Random Dot Product Graph Models for Social Networks
• The method of moments and degree distributions for network models
• Latent Space Approaches to Social Network Analysis
• The eigenvalues of random symmetric matrices
• Stochastic blockmodels with a growing number of classes
• Consistent Adjacency-Spectral Partitioning for the Stochastic Block Model When the Model Parameters Are Unknown
• Representations for partially exchangeable arrays of random variables
• Graph limits and exchangeable random graphs
• A Consistent Adjacency Spectral Embedding for Stochastic Blockmodel Graphs
• Title not available (Why is that?)
• Universally consistent vertex classification for latent positions graphs
• Random matrices: universal properties of eigenvectors
• Eigenvector distribution of Wigner matrices
• Role of normalization in spectral clustering for stochastic blockmodels
• The spectral radii and norms of large dimensional non-central random atrices matrices
• The Largest Eigenvalue of Sparse Random Graphs
• A central limit theorem in the  -model for undirected random graphs with a diverging number of vertices
• The First Eigenvalue of Random Graphs
• Freedman's inequality for matrix martingales

Cited In (30)

• Perfect clustering for stochastic blockmodel graphs via adjacency spectral embedding
• Latent structure blockmodels for Bayesian spectral graph clustering
• Fusing data depth with complex networks: community detection with prior information
• Central limit theorem for fluctuations of linear eigenvalue statistics of large random graphs
• Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectral estimator
• Bayesian estimation of the latent dimension and communities in stochastic blockmodels
• Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals
• Eigenvector delocalization for non‐Hermitian random matrices and applications
• Statistical inference on random dot product graphs: a survey
• Discussion of “Cocitation and Coauthorship Networks of Statisticians”
• On estimation and inference in latent structure random graphs
• Spectral Clustering on Spherical Coordinates Under the Degree-Corrected Stochastic Blockmodel
• Hypothesis testing for equality of latent positions in random graphs
• Eigenvectors and controllability of non-Hermitian random matrices and directed graphs
• Spectral graph clustering via the expectation-solution algorithm
• Maximum A Posteriori Inference of Random Dot Product Graphs via Conic Programming
• Estimating Mixed Memberships With Sharp Eigenvector Deviations
• Empirical Bayes estimation for the stochastic blockmodel
• Title not available (Why is that?)
• Community detection on mixture multilayer networks via regularized tensor decomposition
• Limit theorems for eigenvectors of the normalized Laplacian for random graphs
• Central limit theorems for classical multidimensional scaling
• Efficient Estimation for Random Dot Product Graphs via a One-Step Procedure
• Simultaneous Dimensionality and Complexity Model Selection for Spectral Graph Clustering
• Title not available (Why is that?)
• Robust Recommendation via Social Network Enhanced Matrix Completion
• Vertex nomination, consistent estimation, and adversarial modification
• Spectral analysis of networks with latent space dynamics and signs
• Vertex nomination: the canonical sampling and the extended spectral nomination schemes
• Valid two-sample graph testing via optimal transport procrustes and multiscale graph correlation with applications in connectomics

Uses Software

• mclust

This page was built for publication: A limit theorem for scaled eigenvectors of random dot product graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q288255)