High Dimensional Geometry and Limitations in System Identification

We study the problem of identification of linear dynamical system from a single trajectory, via excitations of isotropic Gaussian. In stark contrast with previously reported results, Ordinary Least Squares (OLS) estimator for even \emph{stable} dynamical system contains non-vanishing error in \emph{high dimensions}; which stems from the fact that realizations of non-diagonalizable dynamics can have strong \emph{spatial correlations} and a variance, of order , where is the dimension of the underlying state space. Employing \emph{concentration of measure phenomenon}, in particular tensorization of \emph{Talagrands inequality} for random dynamical systems we show that observed trajectory of dynamical system of length- can have a variance of order . Consequently, showing some or most of the distances between an dimensional random vector and an dimensional hyperplane in can be close to zero with positive probability and these estimates become stronger in high dimensions and more iterations via \emph{Isoperimetry}. \emph{Negative second moment identity}, along with distance estimates give a control on all the singular values of \emph{Random matrix} of data, revealing limitations of OLS for stable non-diagonalizable and explosive diagonalizable systems.
View on arXiv