Finite Sample Analysis for Structured Discrete System Identification

• 成果类型: Article
• 署名作者: Xie, Xiaotian; Katselis, Dimitrios; Beck, Carolyn L.; Srikant, R.
• 署名单位: Central South University; University of Illinois System; University of Illinois Urbana-Champaign; University of Illinois System; University of Illinois Urbana-Champaign
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2023.3236243
• 发表日期: 2023
• 页码: 6345-6352
• 关键词: Discrete state-space dynamical systems; identification; Markov chains; Sample Complexity

摘要

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.