On-line Bayesian System Identification

TL;DR

This paper introduces a real-time Bayesian system identification method that updates hyper-parameters with a single iteration of optimization, balancing speed and accuracy for on-line applications.

Contribution

It proposes a novel 1-step hyper-parameter update procedure using gradient or EM methods, suitable for real-time system identification.

Findings

The 1-step method performs comparably to full optimization in experiments.

The approach is effective for real-time system identification.

Single-iteration updates significantly reduce computation time.

Abstract

We consider an on-line system identification setting, in which new data become available at given time steps. In order to meet real-time estimation requirements, we propose a tailored Bayesian system identification procedure, in which the hyper-parameters are still updated through Marginal Likelihood maximization, but after only one iteration of a suitable iterative optimization algorithm. Both gradient methods and the EM algorithm are considered for the Marginal Likelihood optimization. We compare this "1-step" procedure with the standard one, in which the optimization method is run until convergence to a local minimum. The experiments we perform confirm the effectiveness of the approach we propose.