Frequency-domain Gaussian Process Models for $H_\infty$ Uncertainties
Abstract
Complex-valued Gaussian processes are commonly used in Bayesian frequency-domain system identification as prior models for regression. If each realization of such a process were an function with probability one, then the same model could be used for probabilistic robust control, allowing for robustly safe learning. We investigate sufficient conditions for a general complex-domain Gaussian process to have this property. For the special case of processes whose Hermitian covariance is stationary, we provide an explicit parameterization of the covariance structure in terms of a summable sequence of nonnegative numbers. We then establish how an Gaussian process can serve as a prior for Bayesian system identification and as a probabilistic uncertainty model for probabilistic robust control. In particular, we compute formulas for refining the uncertainty model by conditioning on frequency-domain data and for upper-bounding the probability that the realizations of the process satisfy a given integral quadratic constraint.
Cite
@article{arxiv.2312.10106,
title = {Frequency-domain Gaussian Process Models for $H_\infty$ Uncertainties},
author = {Alex Devonport and Peter Seiler and Murat Arcak},
journal= {arXiv preprint arXiv:2312.10106},
year = {2023}
}
Comments
20 pages, 2 figures. Submission to SICON. arXiv admin note: substantial text overlap with arXiv:2211.15923