Skip to content

A Tutorial on Concentration Bounds for System Identification

Authors
Nikolai Matni, Stephen Tu
Year
2019
Conference Paper
Source
IEEE 58th Conference on Decision and Control (CDC)
Identifiers
arXiv 1906.11395 DOI 10.1109/cdc40024.2019.9029621

Abstract

We provide a brief tutorial on the use of concentration inequalities as they apply to system identification of state-space parameters of linear time invariant systems, with a focus on the fully observed setting. We draw upon tools from the theories of large-deviations and self-normalized martingales, and provide both data-dependent and independent bounds on the learning rate.

Knowledge Base

Map Tree Search

External

Document arXiv Abstract arXiv PDF arXiv HTML DOI Google Scholar OpenAlex ieeexplore.ieee.org xplorestaging.ieee.org PDF

Tags

System identification Learning State space

Similar Papers