Estimation of sparse linear dynamic networks using the stable spline horseshoe prior

TL;DR

This paper proposes a novel Bayesian method combining stable spline and horseshoe priors for identifying sparse linear dynamic networks, effectively recovering network topology and module dynamics from limited data.

Contribution

Introduces the stable spline horseshoe (SSH) prior, a new Bayesian model that enhances sparse network identification by integrating shrinkage and smoothness priors.

Findings

Accurately reconstructs sparse network dynamics from small datasets.

Efficient MCMC inference tailored for dynamic network models.

Handles thousands of impulse response coefficients effectively.

Abstract

Identification of the so-called dynamic networks is one of the most challenging problems appeared recently in control literature. Such systems consist of large-scale interconnected systems, also called modules. To recover full networks dynamics the two crucial steps are topology detection, where one has to infer from data which connections are active, and modules estimation. Since a small percentage of connections are effective in many real systems, the problem finds also fundamental connections with group-sparse estimation. In particular, in the linear setting modules correspond to unknown impulse responses expected to have null norm but in a small fraction of samples. This paper introduces a new Bayesian approach for linear dynamic networks identification where impulse responses are described through the combination of two particular prior distributions. The first one is a block version of the horseshoe prior, a model possessing important global-local shrinkage features. The second one is the stable spline prior, that encodes information on smooth-exponential decay of the modules. The resulting model is called stable spline horseshoe (SSH) prior. It implements aggressive shrinkage of small impulse responses while larger impulse responses are conveniently subject to stable spline regularization. Inference is performed by a Markov Chain Monte Carlo scheme, tailored to the dynamic context and able to efficiently return the posterior of the modules in sampled form. We include numerical studies that show how the new approach can accurately reconstruct sparse networks dynamics also when thousands of unknown impulse response coefficients must be inferred from data sets of relatively small size.