Non asymptotic estimation lower bounds forLTI state space models with Cramér-Rao and van Trees

• We study the estimation problem for linear time-invariant (LTI) state-space models with Gaussian excitation of an unknown covariance. We provide non asymptotic lower bounds for the expected estimation error and the mean square estimation risk of the least square estimator, and the minimax mean square estimation risk. These bounds are sharp with explicit constants when the matrix of the dynamics has no eigenvalues on the unit circle and are rate-optimal when they do. Our results extend and improve existing lower bounds to lower bounds in expectation of the mean square estimation risk and to systems with a general noise covariance. Instrumental to our derivation are new concentration results for rescaled sample covariances and deviation results for the corresponding multiplication processes of the covariates, a differential geometric construction of a prior on the unit operator ball of small Fisher information, and an extension of the Cramér-Rao and van Treesinequalities to matrix-valued estimators.

Ämnesord

NATURVETENSKAP  -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)

NATURAL SCIENCES  -- Mathematics -- Probability Theory and Statistics (hsv//eng)

Nyckelord

linear time invariant state space models

least squares

on asymptotic estimation

minimax risk

samplecomplexity

sample covariance

multiplication process

concentration inequality

Cramér-Rao

van Trees inequal-ity

Fisher information

Matematisk statistik

Mathematical Statistics

Publikations- och innehållstyp

vet (ämneskategori)

ovr (ämneskategori)