Estimating Mixed Memberships With Sharp Eigenvector Deviations

DOI10.1080/01621459.2020.1751645zbMath1506.62331arXiv1709.00407OpenAlexW3017845708MaRDI QIDQ5881973

Xueyu Mao, Deepayan Chakrabarti, Purnamrita Sarkar

Publication date: 14 March 2023

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1709.00407

zbMATH Keywords

clusteringnetworksasymptotic analysisoverlapping community detection

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectral estimator ⋮ Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals ⋮ Spectral Clustering via Adaptive Layer Aggregation for Multi-Layer Networks ⋮ Assigning topics to documents by successive projections ⋮ The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics ⋮ An \({\ell_p}\) theory of PCA and spectral clustering

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A limit theorem for scaled eigenvectors of random dot product graphs
• Spectral statistics of Erdős-Rényi graphs. I: Local semicircle law
• Community discovery using nonnegative matrix factorization
• Spectral clustering and the high-dimensional stochastic blockmodel
• The (un)supervised NMF methods for discovering overlapping communities as well as hubs and outliers in networks
• A spectral algorithm with additive clustering for the recovery of overlapping communities in networks
• Entrywise eigenvector analysis of random matrices with low expected rank
• The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
• Consistency of spectral clustering in stochastic block models
• Exact Recovery in the Stochastic Block Model
• Improved Graph Clustering
• Mixed membership stochastic blockmodels
• Multidimensional binary search trees used for associative searching
• Efficient discovery of overlapping communities in massive networks
• A useful variant of the Davis–Kahan theorem for statisticians
• Computing a nonnegative matrix factorization -- provably
• Signal-plus-noise matrix models: eigenvector deviations and fluctuations

This page was built for publication: Estimating Mixed Memberships With Sharp Eigenvector Deviations