English

A Tutorial on the Non-Asymptotic Theory of System Identification

Systems and Control 2024-06-18 v2 Machine Learning Systems and Control Machine Learning

Abstract

This tutorial serves as an introduction to recently developed non-asymptotic methods in the theory of -- mainly linear -- system identification. We emphasize tools we deem particularly useful for a range of problems in this domain, such as the covering technique, the Hanson-Wright Inequality and the method of self-normalized martingales. We then employ these tools to give streamlined proofs of the performance of various least-squares based estimators for identifying the parameters in autoregressive models. We conclude by sketching out how the ideas presented herein can be extended to certain nonlinear identification problems.

Keywords

Cite

@article{arxiv.2309.03873,
  title  = {A Tutorial on the Non-Asymptotic Theory of System Identification},
  author = {Ingvar Ziemann and Anastasios Tsiamis and Bruce Lee and Yassir Jedra and Nikolai Matni and George J. Pappas},
  journal= {arXiv preprint arXiv:2309.03873},
  year   = {2024}
}
R2 v1 2026-06-28T12:15:31.748Z