A Tutorial on the Non-Asymptotic Theory of System Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ziemann, Ingvar, Tsiamis, Anastasios, Lee, Bruce, Jedra, Yassir, Matni, Nikolai, Pappas, George J.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913393035706368
author Ziemann, Ingvar
Tsiamis, Anastasios
Lee, Bruce
Jedra, Yassir
Matni, Nikolai
Pappas, George J.
author_facet Ziemann, Ingvar
Tsiamis, Anastasios
Lee, Bruce
Jedra, Yassir
Matni, Nikolai
Pappas, George J.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_03873
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Tutorial on the Non-Asymptotic Theory of System Identification
Ziemann, Ingvar
Tsiamis, Anastasios
Lee, Bruce
Jedra, Yassir
Matni, Nikolai
Pappas, George J.
Systems and Control
Machine Learning
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.
title A Tutorial on the Non-Asymptotic Theory of System Identification
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2309.03873