18
2

High Dimensional Geometry and Limitations in System Identification

Abstract

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 O(en)O(e^{n}), where nn 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-NN can have a variance of order O(enN)O(e^{nN}). Consequently, showing some or most of the nn distances between an NN- dimensional random vector and an (n1)(n-1) dimensional hyperplane in RN\mathbb{R}^{N} 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
Comments on this paper