High precision variational Bayesian inference of sparse linear networks

DOI10.1016/J.AUTOMATICA.2020.109017zbMATH Open1447.93061arXiv1901.00673OpenAlexW3024607720MaRDI QIDQ2188259FDOQ2188259

Authors: Junyang Jin, Ye Yuan, Jorge Goncalves 

Publication date: 10 June 2020

Published in: Automatica (Search for Journal in Brave)

Abstract: Sparse networks can be found in a wide range of applications, such as biological and communication networks. Inference of such networks from data has been receiving considerable attention lately, mainly driven by the need to understand and control internal working mechanisms. However, while most available methods have been successful at predicting many correct links, they also tend to infer many incorrect links. Precision is the ratio between the number of correctly inferred links and all inferred links, and should ideally be close to 100%. For example, 50% precision means that half of inferred links are incorrect, and there is only a 50% chance of picking a correct one. In contrast, this paper develops a method, based on variational Bayesian inference and Gaussian processes, that focuses on inferring links with very high precision. In addition, our method does not require full-state measurements and effectively promotes both system stability and network sparsity. Monte Carlo simulations illustrate that our method has 100% or nearly 100% precision, even in the presence of noise. The method should be applicable to a wide range of network inference contexts, including biological networks and power systems.

Full work available at URL: https://arxiv.org/abs/1901.00673

Recommendations

• Topology identification of sparse network: a stochastic variational Bayesian approach
• A Bayesian approach to sparse dynamic network identification
• Complex networks identification using Bayesian model with independent Laplace prior
• scientific article; zbMATH DE number 7255155
• Network inference and biological dynamics

zbMATH Keywords

variational inferencesystem identificationsparse networksnetwork inferencedynamical structure function

Mathematics Subject Classification ID

Bayesian inference (62F15) Systems biology, networks (92C42) System identification (93B30) Linear systems in control theory (93C05) Networked control (93B70)

Cites Work

• Vectorized adaptive quadrature in MATLAB
• Gaussian processes for machine learning.
• Pattern recognition and machine learning.
• On the estimation of transfer functions, regularizations and Gaussian processes-revisited
• System Identification Via Sparse Multiple Kernel-Based Regularization Using Sequential Convex Optimization Techniques
• Kernel methods in system identification, machine learning and function estimation: a survey
• Prediction error identification of linear systems: a nonparametric Gaussian regression approach
• Robust EM kernel-based methods for linear system identification
• Kernels for Linear Time Invariant System Identification
• A Bayesian approach to sparse dynamic network identification
• Necessary and Sufficient Conditions for Dynamical Structure Reconstruction of LTI Networks
• Sparse plus low rank network identification: a nonparametric approach
• Robust dynamical network structure reconstruction
• A Minimal Realization Technique for the Dynamical Structure Function of a Class of LTI Systems

Cited In (4)

• Sparse estimation in linear dynamic networks using the stable spline horseshoe prior
• Data augmentation-based statistical inference of diffusion processes
• Topology identification of sparse network: a stochastic variational Bayesian approach
• Title not available (Why is that?)

Uses Software

• quadgk
• PRMLT
• quadva

This page was built for publication: High precision variational Bayesian inference of sparse linear networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2188259)