A least-square method for non-asymptotic identification in linear switching control

arXiv:2404.08120v1 Announce Type: cross
Abstract: The focus of this paper is on linear system identification in the setting where it is known that the underlying partially-observed linear dynamical system lies within a finite collection of known candidate models. We first consider the problem of identification from a given trajectory, which in this setting reduces to identifying the index of the true model with high probability. We characterize the finite-time sample complexity of this problem by leveraging recent advances in the …

abstract arxiv collection control cs.lg cs.sy eess.sy focus identification least lies linear math.oc paper square trajectory type