The ubiquity of integrating detectors in imaging and other applications implies that a variety of real-world data are well modeled as Poisson random variables whose means are in turn proportional to an underlying vector-valued signal of interest. In this article, we first show how the so-called Skellam distribution arises from the fact that Haar wavelet and filterbank transform coefficients corresponding to measurements of this type are distributed as sums and differences of Poisson counts. We then provide two main theorems on Skellam shrinkage, one showing the near-optimality of shrinkage in the Bayesian setting and the other providing for unbiased risk estimation in a frequentist context. These results serve to yield new estimators in the Haar transform domain, including an unbiased risk estimate for shrinkage of Haar-Fisz variance-stabilized data, along with accompanying low-complexity algorithms for inference. We conclude with a simulation study demonstrating the efficacy of our Skellam shrinkage estimators both for the standard univariate wavelet test functions as well as a variety of test images taken from the image processing literature, confirming that they offer substantial performance improvements over existing alternatives.
Flexible signal denoising via flexible empirical Bayes shrinkage
信号去噪-也称为非参数回归-通常通过变换后的收缩估计来执行（例如，小波）域;变换域中的收缩对应于原始域中的平滑。这类应用中的一个关键问题是要收缩多少，或者说要平滑多少。经验贝叶斯收缩方法为这个问题提供了一个有吸引力的解决方案;它们使用数据来估计潜在“效应”的分布，从而自动选择适当的收缩量。然而，经验贝叶斯收缩的大多数现有实现都不如它们所能做到的灵活-无论是在它们对效应的潜在分布的假设上，还是在它们处理异方差的能力上-这限制了它们的信号去噪应用。在这里，我们通过采取一种特别灵活，稳定和计算方便的经验贝叶斯收缩方法来解决这个问题，并将其应用于几个信号去噪问题。这些应用包括泊松数据和异方差高斯数据的平滑。我们通过实证比较表明，与其他方法，包括简单的阈值规则和专门建立的经验贝叶斯程序的结果是有竞争力的。我们的方法是在R包smashr中实现的，“Smoothing by Adaptive Shrinkage in R”，可在https://www.github.com/stephenslab/smashr获得
