Empirical Bayesian learning in AR graphical models

DOI10.1016/J.AUTOMATICA.2019.108516zbMATH Open1496.62160arXiv1907.03829OpenAlexW2964468196WikidataQ127393825 ScholiaQ127393825MaRDI QIDQ2280924FDOQ2280924

Authors: Mattia Zorzi 

Publication date: 19 December 2019

Published in: Automatica (Search for Journal in Brave)

Abstract: We address the problem of learning graphical models which correspond to high dimensional autoregressive stationary stochastic processes. A graphical model describes the conditional dependence relations among the components of a stochastic process and represents an important tool in many fields. We propose an empirical Bayes estimator of sparse autoregressive graphical models and latent-variable autoregressive graphical models. Numerical experiments show the benefit to take this Bayesian perspective for learning these types of graphical models.

Full work available at URL: https://arxiv.org/abs/1907.03829

Recommendations

• Bayesian inference for ARFIMA models
• Bayesian structure learning in graphical models
• AR Identification of Latent-Variable Graphical Models
• Bayesian empirical likelihood inference for the generalized binomial AR(1) model
• Empirical Bayesian Learning
• ARMA Identification of Graphical Models
• Graphical models of autoregressive processes
• A Bayesian Approach to Modelling Graphical Vector Autoregressions
• An empirical Bayes procedure for the selection of Gaussian graphical models
• Dynamic and robust Bayesian graphical models

zbMATH Keywords

convex optimizationsparsityconvex relaxationempirical Bayesian learninglow-rank inducing priors

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05) Probabilistic graphical models (62H22) Inference from stochastic processes and spectral analysis (62M15)

Cites Work

• The elements of statistical learning. Data mining, inference, and prediction
• Graphical interaction models for multivariate time series.
• Enhancing sparsity by reweighted \(\ell _{1}\) minimization
• A unified convergence analysis of block successive minimization methods for nonsmooth optimization
• Model selection through sparse maximum likelihood estimation for multivariate Gaussian or binary data
• Title not available (Why is that?)
• Rejoinder: Latent variable graphical model selection via convex optimization
• AR Identification of Latent-Variable Graphical Models
• Multivariate Spectral Estimation Based on the Concept of Optimal Prediction
• A New Family of High-Resolution Multivariate Spectral Estimators
• Time and Spectral Domain Relative Entropy: A New Approach to Multivariate Spectral Estimation
• An interpretation of the dual problem of the THREE-like approaches
• A new approach to spectral estimation: A tunable high-resolution spectral estimator.
• Rational approximations of spectral densities based on the Alpha divergence
• ARMA Identification of Graphical Models
• Uncertainty Bounds for Spectral Estimation
• Topology selection in graphical models of autoregressive processes

Cited In (8)

• New reproducing kernel functions in the reproducing kernel Sobolev spaces
• Graphical models of autoregressive processes
• Adaptive regularised kernel-based identification method for large-scale systems with unknown order
• Graphical model selection for a particular class of continuous-time processes.
• Generalized maximum entropy based identification of graphical ARMA models
• Autoregressive identification of Kronecker graphical models
• Sparse plus low-rank identification for dynamical latent-variable graphical AR models
• Support Recovery and Parameter Identification of Multivariate ARMA Systems with Exogenous Inputs

This page was built for publication: Empirical Bayesian learning in AR graphical models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2280924)