Truncated simulation and inference in edge-exchangeable networks

DOI10.1214/21-EJS1916MaRDI QIDQ2074285zbMATH OpenOpenAlexFDO

Authors Trevor Campbell, Xing-Long Li

Publication date 9 February 2022

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2005.08136, https://projecteuclid.org/journals/electronic-journal-of-statistics/volume-15/issue-2/Truncated-simulation-and-inference-in-edge-exchangeable-networks/10.1214/21-EJS1916.full

zbMATH Keywords

Bayesian inferenceBayesian nonparametricsedge-exchangeablenetworkstruncation

Mathematics Subject Classification ID

Random graphs (graph-theoretic aspects) (05C80) Random measures (60G57) Bayesian inference (62F15) Nonparametric estimation (62G05) Probabilistic graphical models (62H22)

Abstract: Edge-exchangeable probabilistic network models generate edges as an i.i.d.~sequence from a discrete measure, providing a simple means for statistical inference of latent network properties. The measure is often constructed using the self-product of a realization from a Bayesian nonparametric (BNP) discrete prior; but unlike in standard BNP models, the self-product measure prior is not conjugate the likelihood, hindering the development of exact simulation and inference algorithms. Approximation via finite truncation of the discrete measure is a straightforward alternative, but incurs an unknown approximation error. In this paper, we develop methods for forward simulation and posterior inference in random self-product-measure models based on truncation, and provide theoretical guarantees on the quality of the results as a function of the truncation level. The techniques we present are general and extend to the broader class of discrete Bayesian nonparametric models.

Recommendations

• Edge exchangeable models for interaction networks
• Sparse graphs using exchangeable random measures
• An adaptive truncation method for inference in Bayesian nonparametric models
• On exchangeability in network models
• Network representation using graph root distributions

Cites work

• A Bayesian analysis of some nonparametric problems
• A correlated topic model of science
• A Representation of Independent Increment Processes without Gaussian Components
• A statistical framework for modern network science
• Bayesian Density Estimation and Inference Using Mixtures
• Completely random measures
• Edge exchangeable models for interaction networks
• Exact and approximate sum representations for the Dirichlet process
• Exchangeable trait allocations
• Generalized Gamma measures and shot-noise Cox processes
• Gibbs Sampling Methods for Stick-Breaking Priors
• scientific article; zbMATH DE number 1639863 (Why is no real title available?)
• scientific article; zbMATH DE number 3150484 (Why is no real title available?)
• scientific article; zbMATH DE number 2117879 (Why is no real title available?)
• Lectures on the Poisson Process
• Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems
• Nonparametric Bayes estimators based on beta processes in models for life history data
• Nonparametric network models for link prediction
• On edge exchangeable random graphs
• On series representations of infinitely divisible random vectors
• Poisson/gamma random field models for spatial statistics
• Posteriors, conjugacy, and exponential families for completely random measures
• Slice sampling mixture models
• Sparse exchangeable graphs and their limits via graphon processes
• Sparse graphs using exchangeable random measures
• The discrete infinite logistic normal distribution
• The Indian buffet process: an introduction and review
• Truncated random measures
• Variational inference for Dirichlet process mixtures

Cited in

(2)

• Edge exchangeable models for interaction networks
• Posterior sampling from truncated Ferguson-Klass representation of normalised completely random measure mixtures

Describes a project that uses

Uses Software

• BayesDA

This page was built for publication: Truncated simulation and inference in edge-exchangeable networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2074285)