Universally consistent vertex classification for latent positions graphs

DOI10.1214/13-AOS1112zbMath1273.62147arXiv1212.1182OpenAlexW3104477937MaRDI QIDQ366983

Minh Tang, Daniel L. Sussman, Carey E. Priebe

Publication date: 25 September 2013

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1212.1182

zbMATH Keywords

classificationconvex cost functionBayes-risk consistencyconvergence of eigenvectorslatent space model

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Statistical decision theory (62C99) Empirical decision procedures; empirical Bayes procedures (62C12)

Related Items

Community detection and percolation of information in a geometric setting, Maximum A Posteriori Inference of Random Dot Product Graphs via Conic Programming, Motif estimation via subgraph sampling: the fourth-moment phenomenon, A limit theorem for scaled eigenvectors of random dot product graphs, Markov random geometric graph, MRGG: a growth model for temporal dynamic networks, Testing for Equivalence of Network Distribution Using Subgraph Counts, Unnamed Item, Unnamed Item, Stratified Stochastic Variational Inference for High-Dimensional Network Factor Model, Efficient Estimation for Random Dot Product Graphs via a One-Step Procedure, Entropic Optimal Transport on Random Graphs, A probabilistic view of latent space graphs and phase transitions, Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals, Bayesian estimation of the latent dimension and communities in stochastic blockmodels, Exponential-family models of random graphs: inference in finite, super and infinite population scenarios, Perfect clustering for stochastic blockmodel graphs via adjacency spectral embedding, Hyperlink regression via Bregman divergence, Unnamed Item, Unnamed Item, Statistical inference on random dot product graphs: a survey, Adaptive estimation of nonparametric geometric graphs, On the estimation of latent distances using graph distances, Consistent nonparametric estimation for heavy-tailed sparse graphs, Unnamed Item, Unnamed Item, Empirical Bayes estimation for the stochastic blockmodel

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
• Freedman's inequality for matrix martingales
• Spectral clustering and the high-dimensional stochastic blockmodel
• Variation of discrete spectra
• Consistent nonparametric regression. Discussion
• Support vector machines are universally consistent
• On the Bayes-risk consistency of regularized boosting methods.
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Random matrix approximation of spectra of integral operators
• Matrix estimation by universal singular value thresholding
• Statistical performance of support vector machines
• Consistency of spectral clustering
• On the mathematical foundations of learning
• 10.1162/153244302760185252
• Mixed membership stochastic blockmodels
• Learning Eigenfunctions Links Spectral Embedding and Kernel PCA
• Functional Classification in Hilbert Spaces
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• Graph limits and exchangeable random graphs
• Latent Space Approaches to Social Network Analysis
• A Consistent Adjacency Spectral Embedding for Stochastic Blockmodel Graphs
• Learning Theory
• Consistent Adjacency-Spectral Partitioning for the Stochastic Block Model When the Model Parameters Are Unknown
• The phase transition in inhomogeneous random graphs
• Universality, Characteristic Kernels and RKHS Embedding of Measures
• Random Dot Product Graph Models for Social Networks
• Learning Theory
• Learning Theory
• The Rotation of Eigenvectors by a Perturbation. III
• Convexity, Classification, and Risk Bounds