Finite Sample Analysis for Structured Discrete System Identification
Finite Sample Analysis for Structured Discrete System Identification
复制标题
DOI：
10.1109/tac.2023.3236243
复制
发表时间：
2023-10
影响因子：
6.8
通讯作者：
Xiaotian Xie;Dimitrios Katselis;Carolyn L. Beck;R. Srikant
中科院分区：
文献类型：
--
作者：
Xiaotian Xie;Dimitrios Katselis;Carolyn L. Beck;R. Srikant
我们考虑一个离散状态空间上的离散时间动力系统，该系统根据一种称为伯努利自回归（BAR）模型的结构化马尔可夫模型进行演化。我们的目标是为使用间接极大似然估计器估计该模型参数的问题获得样本复杂度界。我们的样本复杂度界限利用BAR模型的结构，并利用随机矩阵和Lipschitz函数的浓度不等式建立。
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.