模型不确定性下Bayes和Wiener估计的稳健性
On the Robustness of the Bayes and Wiener Estimators under Model Uncertainty
摘要:
本文讨论了在有噪声观测下信号的抗差估计问题。我们假设信号和观测值的实际统计量属于关于名义统计量的球。这个球是通过在实际统计量和名义统计量之间的Tau发散族上放置一个界限而形成的。然后,根据球中的最不利统计量,通过最小化均方误差得到鲁棒估计器。因此,我们得到了一个基于分歧族的Minimax方法的鲁棒估计。我们证明了在信号和观测都没有动态的情况下,贝叶斯估计是最优解。此外,在动态的情况下,最佳的离线估计是非因果维纳滤波器。
英文摘要:
This paper deals with the robust estimation problem of a signal given noisy observations. We assume that the actual statistics of the signal and observations belong to a ball about the nominal statistics. This ball is formed by placing a bound on the Tau-divergence family between the actual and the nominal statistics. Then, the robust estimator is obtained by minimizing the mean square error according to the least favorable statistics in that ball. Therefore, we obtain a divergence family-based minimax approach to robust estimation. We show in the case that the signal and observations have no dynamics, the Bayes estimator is the optimal solution. Moreover, in the dynamic case, the optimal offline estimator is the noncausal Wiener filter.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。