Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yuyang, Zhang, Xinhe, Liu, Jia, Li, Na
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.09057
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908519540719616
author Zhang, Yuyang
Zhang, Xinhe
Liu, Jia
Li, Na
author_facet Zhang, Yuyang
Zhang, Xinhe
Liu, Jia
Li, Na
contents This paper addresses the problem of learning linear dynamical systems from noisy observations. In this setting, existing algorithms either yield biased parameter estimates or have large sample complexities. We resolve these issues by adapting the instrumental variable method and the bias compensation method, originally proposed for error-in-variables models, to our setting. We provide refined non-asymptotic analysis for both methods. Under mild conditions, our algorithms achieve superior sample complexities that match the best-known sample complexity for learning a fully observable system without observation noise.
format Preprint
id arxiv_https___arxiv_org_abs_2504_09057
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Error-In-Variables Methods for Efficient System Identification with Finite-Sample Guarantees
Zhang, Yuyang
Zhang, Xinhe
Liu, Jia
Li, Na
Systems and Control
This paper addresses the problem of learning linear dynamical systems from noisy observations. In this setting, existing algorithms either yield biased parameter estimates or have large sample complexities. We resolve these issues by adapting the instrumental variable method and the bias compensation method, originally proposed for error-in-variables models, to our setting. We provide refined non-asymptotic analysis for both methods. Under mild conditions, our algorithms achieve superior sample complexities that match the best-known sample complexity for learning a fully observable system without observation noise.
title Error-In-Variables Methods for Efficient System Identification with Finite-Sample Guarantees
topic Systems and Control
url https://arxiv.org/abs/2504.09057