Statistical learning theory for control: A finite-sample perspective

A Tsiamis, I Ziemann, N Matni… - IEEE Control Systems …, 2023 - ieeexplore.ieee.org
Learning algorithms have become an integral component to modern engineering solutions.
Examples range from self-driving cars and recommender systems to finance and even …

A tutorial on the non-asymptotic theory of system identification

I Ziemann, A Tsiamis, B Lee, Y Jedra… - 2023 62nd IEEE …, 2023 - ieeexplore.ieee.org
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 …

Finite Sample Analysis for a Class of Subspace Identification Methods

J He, I Ziemann, CR Rojas, H Hjalmarsson - arXiv preprint arXiv …, 2024 - arxiv.org
While subspace identification methods (SIMs) are appealing due to their simple
parameterization for MIMO systems and robust numerical realizations, a comprehensive …

[PDF][PDF] Lectures Notes for ESE6180: Learning, Dynamics and Control

I Ziemann - 2024 - ingvarziemann.com
The use of sequential data in modern machine learning solutions is abundant. Recent
success stories range from advances in natural language processing by pre-training large …