Efficient Learning of a Linear Dynamical System with Stability Guarantees

DOI10.1109/TAC.2022.3213770MaRDI QIDQ6360028arXivFDO

Authors Tobias Sutter, Daniel Kuhn

Publication date 6 February 2021

Published in arXiv

Full work available at URL https://doi.org/10.1109/TAC.2022.3213770

Mathematics Subject Classification ID

Systems theory; control (93-XX)

arXiv classification

math.OC cs.IT math.IT

Abstract: We propose a principled method for projecting an arbitrary square matrix to the non-convex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we show that this projection is optimal in an information-theoretic sense and that it simply amounts to shifting the initial matrix by an optimal linear quadratic feedback gain, which can be computed exactly and highly efficiently by solving a standard linear quadratic regulator problem. The proposed approach allows us to learn the system matrix of a stable linear dynamical system from a single trajectory of correlated state observations. The resulting estimator is guaranteed to be stable and offers explicit statistical bounds on the estimation error.

This page was built for publication: Efficient Learning of a Linear Dynamical System with Stability Guarantees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6360028)