Optimal Centered Active Excitation in Linear System Identification

The paper introduces an active learning algorithm for linear system identification that uses optimal centered noise excitation. It employs ordinary least squares and semidefinite programming to achieve minimal sample complexity while enabling efficient computation of the system matrix estimate. The authors provide both lower and upper bounds on sample complexity that match up to universal factors and explicitly depend on system parameters such as state dimension.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.