A Scalable Strategy for the Identification of Latent-variable Graphical Models

TL;DR

This paper introduces a scalable method for identifying latent-variable graphical models in AR Gaussian processes, leveraging reciprocal process approximations and convex optimization to improve efficiency for large-scale problems.

Contribution

The paper presents a novel identification approach that uses reciprocal process approximation and convex programming, enhancing scalability for high-order AR Gaussian models.

Findings

The proposed method outperforms existing techniques in large-scale scenarios.

Numerical examples demonstrate improved computational efficiency.

The approach effectively captures latent-variable structures in AR models.

Abstract

In this paper we propose an identification method for latent-variable graphical models associated to autoregressive (AR) Gaussian stationary processes. The identification procedure exploits the approximation of AR processes through stationary reciprocal processes thus benefiting of the numerical advantages of dealing with block-circulant matrices. These advantages become more and more significant as the order of the process gets large. We show how the identification can be cast in a regularized convex program and we present numerical examples that compares the performances of the proposed method with the existing ones.