AR Identification of Latent-variable Graphical Models

TL;DR

This paper introduces a novel identification method for autoregressive Gaussian processes with latent variables, leveraging sparse plus low-rank spectral density decomposition and convex relaxations to improve model inference.

Contribution

It presents a new convex relaxation-based approach for identifying latent-variable graphical models in autoregressive Gaussian processes.

Findings

Effective spectral density decomposition technique

Improved identification of latent-variable models

Utilization of convex relaxations enhances computational efficiency

Abstract

The paper proposes an identification procedure for autoregressive gaussian stationary stochastic processes wherein the manifest (or observed) variables are mostly related through a limited number of latent (or hidden) variables. The method exploits the sparse plus low-rank decomposition of the inverse of the manifest spectral density and the efficient convex relaxations recently proposed for such decomposition.