Tuning-free heterogeneous inference in massive networks

DOI10.1080/01621459.2018.1537920zbMATH Open1428.62098arXiv1606.03803OpenAlexW2905419188WikidataQ128753214 ScholiaQ128753214MaRDI QIDQ148592FDOQ148592

Authors: Zhao Ren, Yongjian Kang, Yingying Fan, Jinchi Lv, Zhao Ren, Yongjian Kang, Yingying Fan, Jinchi Lv 

Publication date: 13 June 2016

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

Abstract: Heterogeneity is often natural in many contemporary applications involving massive data. While posing new challenges to effective learning, it can play a crucial role in powering meaningful scientific discoveries through the understanding of important differences among subpopulations of interest. In this paper, we exploit multiple networks with Gaussian graphs to encode the connectivity patterns of a large number of features on the subpopulations. To uncover the heterogeneity of these structures across subpopulations, we suggest a new framework of tuning-free heterogeneity pursuit (THP) via large-scale inference, where the number of networks is allowed to diverge. In particular, two new tests, the chi-based test and the linear functional-based test, are introduced and their asymptotic null distributions are established. Under mild regularity conditions, we establish that both tests are optimal in achieving the testable region boundary and the sample size requirement for the latter test is minimal. Both theoretical guarantees and the tuning-free feature stem from efficient multiple-network estimation by our newly suggested approach of heterogeneous group square-root Lasso (HGSL) for high-dimensional multi-response regression with heterogeneous noises. To solve this convex program, we further introduce a tuning-free algorithm that is scalable and enjoys provable convergence to the global optimum. Both computational and theoretical advantages of our procedure are elucidated through simulation and real data examples.

Full work available at URL: https://arxiv.org/abs/1606.03803

Recommendations

• A partially linear framework for massive heterogeneous data
• Two-sample hypothesis testing for inhomogeneous random graphs
• Heterogeneous reciprocal graphical models
• Estimation of multiple networks in Gaussian mixture models
• A global homogeneity test for high-dimensional linear regression

zbMATH Keywords

multiple networksefficiencysparsityhigh dimensionalityheterogeneous group square-root Lassoheterogeneous learninglarge-scale inferencescalability

Mathematics Subject Classification ID

Point estimation (62F10) Asymptotic properties of parametric estimators (62F12) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Asymptotic distribution theory in statistics (62E20)

Cites Work

• Title not available (Why is that?)
• Asymptotic normality and optimalities in estimation of large Gaussian graphical models
• Gaussian graphical model estimation with false discovery rate control
• Graphical models, exponential families, and variational inference
• Title not available (Why is that?)
• High-dimensional graphs and variable selection with the Lasso
• The benefit of group sparsity in group inference with de-biased scaled group Lasso
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• Title not available (Why is that?)
• Model Selection and Estimation in Regression with Grouped Variables
• Sparse inverse covariance estimation with the graphical lasso
• Network exploration via the adaptive LASSO and SCAD penalties
• Scaled sparse linear regression
• Model selection and estimation in the Gaussian graphical model
• Title not available (Why is that?)
• Joint estimation of multiple graphical models
• The Joint Graphical Lasso for Inverse Covariance Estimation Across Multiple Classes
• High-dimensional covariance estimation by minimizing \(\ell _{1}\)-penalized log-determinant divergence
• High dimensional inverse covariance matrix estimation via linear programming
• A constrained \(\ell _{1}\) minimization approach to sparse precision matrix estimation
• Adaptive estimation of a quadratic functional by model selection.
• Nonparametric goodness-of-fit testing under Gaussian models
• Non-asymptotic minimax rates of testing in signal detection
• Time varying undirected graphs
• Minimax estimation of linear and quadratic functionals on sparsity classes
• Covariance and precision matrix estimation for high-dimensional time series
• Joint estimation of multiple high-dimensional precision matrices
• Innovated scalable efficient estimation in ultra-large Gaussian graphical models
• Maximum Likelihood Estimation of a Multi-Dimensional Log-Concave Density
• Structural Pursuit Over Multiple Undirected Graphs
• The Group Square-Root Lasso: Theoretical Properties and Fast Algorithms
• Joint Estimation of Multiple Graphical Models from High Dimensional Time Series
• Sparse precision matrix estimation via lasso penalized D-trace loss
• Scalable Algorithms for Data and Network Analysis
• Oracle inequalities and optimal inference under group sparsity
• Estimating time-varying networks
• The benefit of group sparsity

Cited In (4)

• Inference on Multi-level Partial Correlations Based on Multi-subject Time Series Data
• RANK: Large-Scale Inference With Graphical Nonlinear Knockoffs
• Hypothesis testing for high-dimensional multivariate regression with false discovery rate control
• HGSL

Uses Software

• glasso
• LogConcDEAD
• camel
• SOFAR

This page was built for publication: Tuning-free heterogeneous inference in massive networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q148592)