Bayesian cyclic bounds for periodic parameter estimation

In many practical periodic parameter estimation problems, the appropriate cost function is periodic with respect to the unknown parameter. In this paper a new class of cyclic Bayesian lower bounds on the mean cyclic error (MCE) is developed. The new class includes the cyclic version of the Bayesian Cramér-Rao bound (BCRB). The cyclic BCRB requires milder regularity conditions compared to the conventional BCRB. The tightest bound in the proposed class is derived and it is shown that under a certain condition it achieves the minimum MCE (MMCE). The new lower bounds are compared with the cyclic version of the Ziv-Zakai lower bound (ZZLB) and the MCE´s of the MMCE and maximum aposteriori probability (MAP) estimators for frequency estimation with uniform a-priori probability density function (pdf) of the unknown parameter. In this common estimation problem, the conventional BCRB does not exist, while the proposed cyclic BCRB provides a valid lower bound for parameter estimation.