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 use a weighted least squares approach, and provide finite sample error bounds of the learned model as a function of the number of samples and various system parameters from the two systems as well as the weight assigned to the auxiliary data.
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.