Simultaneous Clustering and Estimation of Heterogeneous Graphical Models

zbMATH Open1473.62220arXiv1611.09391MaRDI QIDQ4558554FDOQ4558554

Yufeng Liu, Wei Sun, Guang Cheng, Botao Hao

Publication date: 22 November 2018

Abstract: We consider joint estimation of multiple graphical models arising from heterogeneous and high-dimensional observations. Unlike most previous approaches which assume that the cluster structure is given in advance, an appealing feature of our method is to learn cluster structure while estimating heterogeneous graphical models. This is achieved via a high dimensional version of Expectation Conditional Maximization (ECM) algorithm (Meng and Rubin, 1993). A joint graphical lasso penalty is imposed on the conditional maximization step to extract both homogeneity and heterogeneity components across all clusters. Our algorithm is computationally efficient due to fast sparse learning routines and can be implemented without unsupervised learning knowledge. The superior performance of our method is demonstrated by extensive experiments and its application to a Glioblastoma cancer dataset reveals some new insights in understanding the Glioblastoma cancer. In theory, a non-asymptotic error bound is established for the output directly from our high dimensional ECM algorithm, and it consists of two quantities: statistical error (statistical accuracy) and optimization error (computational complexity). Such a result gives a theoretical guideline in terminating our ECM iterations.

Full work available at URL: https://arxiv.org/abs/1611.09391

zbMATH Keywords

clusteringgraphical modelshigh-dimensional statisticsnon-convex optimizationfinite-sample analysis

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Probabilistic graphical models (62H22)

Cites Work

• Title not available (Why is that?)
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• Maximum likelihood estimation via the ECM algorithm: A general framework
• Sure Independence Screening for Ultrahigh Dimensional Feature Space
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers
• Covariance regularization by thresholding
• Sparse inverse covariance estimation with the graphical lasso
• Network exploration via the adaptive LASSO and SCAD penalties
• The EM Algorithm and Extensions, 2E
• Model selection and estimation in the Gaussian graphical model
• Title not available (Why is that?)
• Partial Correlation Estimation by Joint Sparse Regression Models
• Title not available (Why is that?)
• Penalized likelihood methods for estimation of sparse high-dimensional directed acyclic graphs
• Joint estimation of multiple graphical models
• The Joint Graphical Lasso for Inverse Covariance Estimation Across Multiple Classes
• Bayesian Inference of Multiple Gaussian Graphical Models
• A Constrainedℓ₁Minimization Approach to Sparse Precision Matrix Estimation
• Likelihood-Based Selection and Sharp Parameter Estimation
• Estimation of multiple networks in Gaussian mixture models
• Joint estimation of multiple high-dimensional precision matrices
• Estimating sparse precision matrix: optimal rates of convergence and adaptive estimation
• Structural Pursuit Over Multiple Undirected Graphs
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Joint Estimation of Multiple Graphical Models from High Dimensional Time Series
• Penalized model-based clustering with unconstrained covariance matrices
• Regularized \(k\)-means clustering of high-dimensional data and its asymptotic consistency
• Consistent selection of the number of clusters via crossvalidation
• Joint estimation of precision matrices in heterogeneous populations
• Joint estimation of sparse multivariate regression and conditional graphical models
• On the existence of the weighted bridge penalized Gaussian likelihood precision matrix estimator
• On strong identifiability and convergence rates of parameter estimation in finite mixtures
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (26)

• Model-Based Tensor Low-Rank Clustering
• Simultaneous Cluster Structure Learning and Estimation of Heterogeneous Graphs for Matrix-Variate fMRI Data
• Joint Gaussian graphical model estimation: a survey
• Dynamic Tensor Clustering
• A Bayesian approach for subgroup analysis
• Bayesian inference of clustering and multiple Gaussian graphical models selection
• Title not available (Why is that?)
• Integrative network learning for multimodality biomarker data
• Singularity, misspecification and the convergence rate of EM
• Tuning-free sparse clustering via alternating hard-thresholding
• A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering
• Bayesian Edge Regression in Undirected Graphical Models to Characterize Interpatient Heterogeneity in Cancer
• Detecting clusters in multivariate response regression
• Algorithm 1045: a covariate-dependent approach to Gaussian graphical modeling in R
• Integrating approximate single factor graphical models
• Gaussian mixture models with concave penalized fusion
• A Unified Framework for Structured Graph Learning via Spectral Constraints
• Bayesian sparse seemingly unrelated regressions model with variable selection and covariance estimation via the horseshoe+
• Analysis of heterogeneous networks with unknown dependence structure
• Estimating Multiple Precision Matrices With Cluster Fusion Regularization
• Finding Non-Overlapping Clusters for Generalized Inference Over Graphical Models
• Identifying graph clusters using variational inference and links to covariance parametrization
• Estimation of multiple networks with common structures in heterogeneous subgroups
• Estimating heterogeneous gene regulatory networks from zero-inflated single-cell expression data
• Gaussian graphical model‐based heterogeneity analysis via penalized fusion
• Poststratification fusion learning in longitudinal data analysis

Uses Software

• glasso

   Recommendations

• High-Dimensional Inference for Cluster-Based Graphical Models 👍 👎
• Simultaneous Cluster Structure Learning and Estimation of Heterogeneous Graphs for Matrix-Variate fMRI Data 👍 👎
• Bayesian inference of clustering and multiple Gaussian graphical models selection 👍 👎
• Efficient, certifiably optimal clustering with applications to latent variable graphical models 👍 👎
• The cluster graphical Lasso for improved estimation of Gaussian graphical models 👍 👎
• Simultaneous Semiparametric Estimation of Clustering and Regression 👍 👎
• Identifying graph clusters using variational inference and links to covariance parametrization 👍 👎
• A novel probabilistic clustering model for heterogeneous networks 👍 👎
• Simultaneous Dimensionality and Complexity Model Selection for Spectral Graph Clustering 👍 👎
• Finding Non-Overlapping Clusters for Generalized Inference Over Graphical Models 👍 👎

This page was built for publication: Simultaneous Clustering and Estimation of Heterogeneous Graphical Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558554)