Saved in:
Bibliographic Details
Main Authors: Simpson, Léo, Baumgärtner, Katrin, Köhler, Johannes, Diehl, Moritz
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915875740712960
author Simpson, Léo
Baumgärtner, Katrin
Köhler, Johannes
Diehl, Moritz
author_facet Simpson, Léo
Baumgärtner, Katrin
Köhler, Johannes
Diehl, Moritz
contents This paper presents uniform-in-time finite-sample bounds for regularized linear regression with vector-valued outputs and conditionally zero-mean subgaussian noise. By revisiting classical self-normalized martingale arguments, we obtain bounds that apply directly to multi-output regression, unlike most of the prior work. Compared to the state of the art, the new results are more general and yield tighter bounds, even for scalar-valued outputs. The mild assumptions we use allow for unknown dependencies between regressors and past noise terms, typically induced by system dynamics or feedback mechanisms. Therefore, these novel finite-sample bounds can be applied to many affine-in-parameter system identification problems, including the identification of a linear time-invariant system from full-state measurements. These new results may lead to significant improvements in stochastic learning-based controllers for safety-critical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19073
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Finite-sample bounds for multi-output system identification
Simpson, Léo
Baumgärtner, Katrin
Köhler, Johannes
Diehl, Moritz
Statistics Theory
Dynamical Systems
This paper presents uniform-in-time finite-sample bounds for regularized linear regression with vector-valued outputs and conditionally zero-mean subgaussian noise. By revisiting classical self-normalized martingale arguments, we obtain bounds that apply directly to multi-output regression, unlike most of the prior work. Compared to the state of the art, the new results are more general and yield tighter bounds, even for scalar-valued outputs. The mild assumptions we use allow for unknown dependencies between regressors and past noise terms, typically induced by system dynamics or feedback mechanisms. Therefore, these novel finite-sample bounds can be applied to many affine-in-parameter system identification problems, including the identification of a linear time-invariant system from full-state measurements. These new results may lead to significant improvements in stochastic learning-based controllers for safety-critical applications.
title Finite-sample bounds for multi-output system identification
topic Statistics Theory
Dynamical Systems
url https://arxiv.org/abs/2603.19073