2016/10/03 by Giulio Bottegal, Bottegal, Giulio, Håkan Hjalmarsson +3
Computer Science · Engineering · Mathematics · #Control Systems and Identification #FOS: Computer and information sciences #FOS: Electrical engineering #Gaussian Processes and Bayesian Inference #Machine Learning (stat.ML) #Statistical Methods and Inference #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1610.00470
openalex publication_date 2016/10/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper we introduce a novel method for linear system identification\nwith quantized output data. We model the impulse response as a zero-mean\nGaussian process whose covariance (kernel) is given by the recently proposed\nstable spline kernel, which encodes information on regularity and exponential\nstability. This serves as a starting point to cast our system identification\nproblem into a Bayesian framework. We employ Markov Chain Monte Carlo methods\nto provide an estimate of the system. In particular, we design two methods\nbased on the so-called Gibbs sampler that allow also to estimate the kernel\nhyperparameters by marginal likelihood maximization via the\nexpectation-maximization method. Numerical simulations show the effectiveness\nof the proposed scheme, as compared to the state-of-the-art kernel-based\nmethods when these are employed in system identification with quantized data.\n