no code implementations • 30 Nov 2023 • Lei Xin, George Chiu, Shreyas Sundaram
We develop a data-dependent threshold that can be used in our test that allows one to achieve a pre-specified upper bound on the probability of making a false alarm.
no code implementations • 15 Sep 2023 • Lei Xin, George Chiu, Shreyas Sundaram
Identifying a linear system model from data has wide applications in control theory.
no code implementations • 8 Feb 2023 • Lei Xin, Lintao Ye, George Chiu, Shreyas Sundaram
We consider the problem of learning the dynamics of a linear system when one has access to data generated by an auxiliary system that shares similar (but not identical) dynamics, in addition to data from the true system.
no code implementations • 12 Sep 2022 • Lei Xin, George Chiu, Shreyas Sundaram
We provide non-asymptotic bounds on the estimation error, leveraging the statistical properties of the underlying model.
1 code implementation • 11 Apr 2022 • Lei Xin, Lintao Ye, George Chiu, Shreyas Sundaram
We study the problem of identifying the dynamics of a linear system when one has access to samples generated by a similar (but not identical) system, in addition to data from the true system.
no code implementations • 24 Mar 2022 • Lei Xin, George Chiu, Shreyas Sundaram
Existing results on learning rate and consistency of autonomous linear system identification rely on observations of steady state behaviors from a single long trajectory, and are not applicable to unstable systems.