High-Dimensional Dynamic Systems Identification with Additional Constraints

by   Junlin Li, et al.

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.


page 1

page 2

page 3

page 4


Low-rank matrix completion and denoising under Poisson noise

This paper considers the problem of estimating a low-rank matrix from th...

Multi-weight Nuclear Norm Minimization for Low-rank Matrix Recovery in Presence of Subspace Prior Information

Weighted nuclear norm minimization has been recently recognized as a tec...

RIP-based performance guarantee for low-tubal-rank tensor recovery

The essential task of multi-dimensional data analysis focuses on the ten...

System Identification via Nuclear Norm Regularization

This paper studies the problem of identifying low-order linear systems v...

Learning Parameters for Weighted Matrix Completion via Empirical Estimation

Recently theoretical guarantees have been obtained for matrix completion...

KL property of exponent 1/2 of ℓ_2,0-norm and DC regularized factorizations for low-rank matrix recovery

This paper is concerned with the factorization form of the rank regulari...

Tuning parameter selection rules for nuclear norm regularized multivariate linear regression

We consider the tuning parameter selection rules for nuclear norm regula...

Please sign up or login with your details

Forgot password? Click here to reset