arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.04607cs.ITmath.IT
收藏

营养参数下Fisher信息的不等式与逼近

Inequalities and Approximations for Fisher Information in the Presence of Nuisance Parameters

Eric Clarkson

摘要:

许多成像系统用于估计与被成像的对象相关联的参数的矢量。在许多情况下,在成像数据的模型中存在对于手头的任务不感兴趣的其他参数。我们将这些称为滋扰参数,并使用它们来形成滋扰参数向量的分量。如果我们有一个先验概率分布函数(PDF)的滋扰参数向量,那么我们可以mariginalize滋扰参数,以产生一个条件PDF的数据,只取决于感兴趣的参数。我们将研究这种方法,以开发的不平等和近似的数据时,滋扰参数的影响。

英文摘要:

Many imaging systems are used to estimate a vector of parameters associated with the object being imaged. In many cases there are other parameters in the model for the imaging data that are not of interest for the task at hand. We refer to these as nuisance parameters and use them to form the components of the nuisance parameter vector. If we have a prior probability distribution function (PDF) for the nuisance parameter vector, then we may mariginalize over the nuisance parameters to produce a conditional PDF for the data that only depends on the parameters of interest. We will examine this approach to develop inequalities and approximations for the FIM when the data is affected by nuisance parameters.

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。

↑