System Identification via Nuclear Norm Regularization

  title={System Identification via Nuclear Norm Regularization},
  author={Yue Sun and Samet Oymak and Maryam Fazel},
This paper studies the problem of identifying low-order linear systems via Hankel nuclear norm regularization. Hankel regularization encourages the low-rankness of the Hankel matrix, which maps to the low-orderness of the system. We provide novel statistical analysis for this regularization and carefully contrast it with the unregularized ordinary least-squares (OLS) estimator.Ouranalysis leads to new bounds on estimating the impulse response and the Hankel matrix associated with the linear… 

Figures and Tables from this paper



Nonparametric Finite Time LTI System Identification

This work provides a data-dependent scheme for order selection and finds an accurate realization of system parameters, corresponding to that order, by an approach that is closely related to the Ho-Kalman subspace algorithm.

System identification with missing data via nuclear norm regularization

NucID is found to consistently identify systems with missing data within the imposed error tolerance, a task at which the standard methods sometimes fail, and to be particularly effective when the data is missing with patterns, e.g., on multi-rate systems, where it clearly outperforms existing procedures.

Simple Bounds for Noisy Linear Inverse Problems with Exact Side Information

It is shown that, if precise information about the value f(x_0) or the l_2-norm of the noise is available, one can do a particularly good job at estimation, and the reconstruction error becomes proportional to the “sparsity” of the signal rather than to the ambient dimension of the Noise vector.

Estimation with Norm Regularization

This paper characterize the restricted error set, establish relations between error sets for the constrained and regularized problems, and present an estimation error bound applicable to any norm.

Hankel Matrix Rank Minimization with Applications to System Identification and Realization

We introduce a flexible optimization framework for nuclear norm minimization of matrices with linear structure, including Hankel, Toeplitz, and moment structures and catalog applications from diverse

Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification

It is proved that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajectory, and generalizes the technique to provide bounds for a more general class of linear response time-series.

Robust recovery of complex exponential signals from random Gaussian projections via low rank Hankel matrix reconstruction

Finite Sample Analysis of Stochastic System Identification

This analysis uses recent results from random matrix theory, self-normalized martingales and SVD robustness, in order to show that with high probability the estimation errors decrease with a rate of $1/\sqrt N$ up to logarithmic terms.

Learning Linear Dynamical Systems with Semi-Parametric Least Squares

It is demonstrated that prefiltered least squares yields the first algorithm that provably estimates the parameters of partially-observed linear systems that attains rates which do not not incur a worst-case dependence on the rate at which these dependencies decay.

Nuclear norm system identification with missing inputs and outputs