Finite Sample Analysis for Structured Discrete System Identification

Xiaotian Xie; Dimitrios Katselis; Carolyn L. Beck; R. Srikant

doi:10.1109/TAC.2023.3236243

Finite Sample Analysis for Structured Discrete System Identification

Xiaotian Xie, Dimitrios Katselis, Carolyn L. Beck, R. Srikant

Research output: Contribution to journal › Article › peer-review

Abstract

We consider a discrete-time dynamical system over a discrete state-space, which evolves according to a structured Markov model called Bernoulli autoregressive (BAR) model. Our goal is to obtain sample complexity bounds for the problem of estimating the parameters of this model using an indirect maximum likelihood estimator. Our sample complexity bounds exploit the structure of the BAR model and are established using concentration inequalities for random matrices and Lipschitz functions.

Original language	English (US)
Pages (from-to)	6345-6352
Number of pages	8
Journal	IEEE Transactions on Automatic Control
Volume	68
Issue number	10
DOIs	https://doi.org/10.1109/TAC.2023.3236243
State	Published - Oct 1 2023

Keywords

Discrete state-space dynamical systems
Markov chains
identification
sample complexity

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science Applications
Electrical and Electronic Engineering

Online availability

10.1109/TAC.2023.3236243

Library availability

Discover UIUC Full Text

Cite this

@article{0161043c0e5b4e5ca3b7942dbf1788f8,

title = "Finite Sample Analysis for Structured Discrete System Identification",

abstract = "We consider a discrete-time dynamical system over a discrete state-space, which evolves according to a structured Markov model called Bernoulli autoregressive (BAR) model. Our goal is to obtain sample complexity bounds for the problem of estimating the parameters of this model using an indirect maximum likelihood estimator. Our sample complexity bounds exploit the structure of the BAR model and are established using concentration inequalities for random matrices and Lipschitz functions.",

keywords = "Discrete state-space dynamical systems, Markov chains, identification, sample complexity",

author = "Xiaotian Xie and Dimitrios Katselis and Beck, {Carolyn L.} and R. Srikant",

note = "This work was supported in part by NSF under Grant CCF 17-04970 and Grant ECCS 20-32321 and in part by ONR under Grant N00014-19-1-2566.",

year = "2023",

month = oct,

day = "1",

doi = "10.1109/TAC.2023.3236243",

language = "English (US)",

volume = "68",

pages = "6345--6352",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - Finite Sample Analysis for Structured Discrete System Identification

AU - Xie, Xiaotian

AU - Katselis, Dimitrios

AU - Beck, Carolyn L.

AU - Srikant, R.

N1 - This work was supported in part by NSF under Grant CCF 17-04970 and Grant ECCS 20-32321 and in part by ONR under Grant N00014-19-1-2566.

PY - 2023/10/1

Y1 - 2023/10/1

N2 - We consider a discrete-time dynamical system over a discrete state-space, which evolves according to a structured Markov model called Bernoulli autoregressive (BAR) model. Our goal is to obtain sample complexity bounds for the problem of estimating the parameters of this model using an indirect maximum likelihood estimator. Our sample complexity bounds exploit the structure of the BAR model and are established using concentration inequalities for random matrices and Lipschitz functions.

AB - We consider a discrete-time dynamical system over a discrete state-space, which evolves according to a structured Markov model called Bernoulli autoregressive (BAR) model. Our goal is to obtain sample complexity bounds for the problem of estimating the parameters of this model using an indirect maximum likelihood estimator. Our sample complexity bounds exploit the structure of the BAR model and are established using concentration inequalities for random matrices and Lipschitz functions.

KW - Discrete state-space dynamical systems

KW - Markov chains

KW - identification

KW - sample complexity

UR - http://www.scopus.com/inward/record.url?scp=85147221847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85147221847&partnerID=8YFLogxK

U2 - 10.1109/TAC.2023.3236243

DO - 10.1109/TAC.2023.3236243

M3 - Article

AN - SCOPUS:85147221847

SN - 0018-9286

VL - 68

SP - 6345

EP - 6352

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 10

ER -

Finite Sample Analysis for Structured Discrete System Identification

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this