Learning linear dynamical systems under convex constraints

arXiv:2303.15121v3 Announce Type: replace-cross
Abstract: We consider the problem of finite-time identification of linear dynamical systems from $T$ samples of a single trajectory. Recent results have predominantly focused on the setup where no structural assumption is made on the system matrix $A^* \in \mathbb{R}^{n \times n}$, and have consequently analyzed the ordinary least squares (OLS) estimator in detail. We assume prior structural information on $A^*$ is available, which can be captured in the form of a convex set $\mathcal{K}$ containing …

abstract arxiv constraints cs.sy eess.sy identification least linear math.oc math.st matrix ordinary results samples setup stat.ml stat.th systems trajectory type