Exact Recovery for System Identification with More Corrupt Data than Clean Data

arXiv:2305.10506v3 Announce Type: replace
Abstract: This paper investigates the system identification problem for linear discrete-time systems under adversaries and analyzes two lasso-type estimators. We examine both asymptotic and non-asymptotic properties of these estimators in two separate scenarios, corresponding to deterministic and stochastic models for the attack times. Since the samples collected from the system are correlated, the existing results on lasso are not applicable. We prove that when the system is stable and attacks are injected periodically, the sample complexity …

abstract arxiv clean data corrupt data cs.lg data identification lasso linear math.oc paper recovery stochastic systems type