On LMVDR Estimators for LDSS Models: Conditions for Existence and Further Applications

Eric Chaumette (1) , François Vincent (1) , Benoit Priot (1) , Gaël Pages (1) , Arnaud Dion (2)

1 DEOS - Département Electronique, Optronique et Signal
2 DISC - Département d'Ingénierie des Systèmes Complexes

For linear discrete state-space models, under certain conditions, the linear least mean squares (LLMS) filter estimate has a recursive format, a.k.a. the Kalman filter (KF). Interestingly, the linear minimum variance distortionless response (LMVDR) filter, when it exists, shares exactly the same recursion as the KF, except for the initialization. If LMVDR estimators are suboptimal in mean-squared error sense, they do not depend on the prior knowledge on the initial state. Thus, the LMVDR estimators may outperform the usual LLMS estimators in case of misspecification of the prior knowledge on the initial state. In this perspective, we establish the general conditions under which existence of the LMVDRF is guaranteed. An immediate benefit is the introduction of LMVDR fixed-point and fixed-lag smoothers (and possibly other smoothers or predictors), which has not been possible so far. Indeed, the LMVDR fixed-point smoother can be used to compute recursively the solution of a generalization of the deterministic least-squares problem.

Mots clés: Filtering; Minimum mean-squared error (MSE) upper bound; Smoothing; State estimation; Unbiased filter

Domaines: Systèmes dynamiques [math.DS]; Traitement du signal et de l'image [eess.SP]

Eric Chaumette, François Vincent, Benoit Priot, Gaël Pages, Arnaud Dion. On LMVDR Estimators for LDSS Models: Conditions for Existence and Further Applications. IEEE Transactions on Automatic Control, 2019, 64 (6), pp.2598-2605. ⟨10.1109/TAC.2018.2868239⟩. ⟨hal-02269674⟩