English

High-Dimensional Dynamic Systems Identification with Additional Constraints

Statistics Theory 2019-12-23 v1 Statistics Theory

Abstract

This note presents a unified analysis of the identification of dynamical systems with low-rank constraints under high-dimensional scaling. This identification problem for dynamic systems are challenging due to the intrinsic dependency of the data. To alleviate this problem, we first formulate this identification problem into a multivariate linear regression problem with row-sub-Gaussian measurement matrix using the more general input designs and the independent repeated sampling schemes. We then propose a nuclear norm heuristic method that estimates the parameter matrix of dynamic system from a few input-state data samples. Based on this, we can extend the existing results. In this paper, we consider two scenarios. (i) In the noiseless scenario, nuclear-norm minimization is introduced for promoting low-rank. We define the notion of weak restricted isometry property, which is weaker than the ordinary restricted isometry property, and show it holds with high probability for the row-sub-Gaussian measurement matrix. Thereby, the rank-minimization matrix can be exactly recovered from finite number of data samples. (ii) In the noisy scenario, a regularized framework involving nuclear norm penalty is established. We give the notion of operator norm curvature condition for the loss function, and show it holds for row-sub-Gaussian measurement matrix with high probability. Consequently, when specifying the suitable choice of the regularization parameter, the operator norm error of the optimal solution of this program has a sharp bound given a finite amount of data samples. This operator norm error bound is stronger than the ordinary Frobenius norm error bound obtained in the existing work.

Keywords

Cite

@article{arxiv.1912.09767,
  title  = {High-Dimensional Dynamic Systems Identification with Additional Constraints},
  author = {Junlin Li},
  journal= {arXiv preprint arXiv:1912.09767},
  year   = {2019}
}
R2 v1 2026-06-23T12:52:18.564Z