arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.08993math.STstat.TH
收藏

部分观测的贝叶斯逆问题

Bayesian inverse problems with partial observations

Shota Gugushvili, Aad van der Vaart, Dong Yan

摘要:

研究了离散观测下线性反问题的非参数贝叶斯方法。我们使用离散的傅里叶变换将我们的模型转换成一个截断的高斯序列模型,这是密切相关的经典高斯序列模型。在将截断的序列先验放置在未知参数上后,我们表明,随着观测数$n\rightarrow\infty,$的增加,相应的后验分布围绕真实参数收缩,收缩率取决于真实参数和先验的平滑度以及问题的不适定性程度。这些值的正确组合导致最佳的后验收缩率(对数因子)。类似地,贝叶斯可信集的频率论覆盖率取决于真实参数和先验的平滑性以及问题的不适定性的组合。过度平滑先验导致零覆盖,而欠平滑先验产生高度保守的结果。最后,我们通过数值例子来说明我们的理论结果。

英文摘要:

We study a nonparametric Bayesian approach to linear inverse problems under discrete observations. We use the discrete Fourier transform to convert our model into a truncated Gaussian sequence model, that is closely related to the classical Gaussian sequence model. Upon placing the truncated series prior on the unknown parameter, we show that as the number of observations $n\rightarrow\infty,$ the corresponding posterior distribution contracts around the true parameter at a rate depending on the smoothness of the true parameter and the prior, and the ill-posedness degree of the problem. Correct combinations of these values lead to optimal posterior contraction rates (up to logarithmic factors). Similarly, the frequentist coverage of Bayesian credible sets is shown to be dependent on a combination of smoothness of the true parameter and the prior, and the ill-posedness of the problem. Oversmoothing priors lead to zero coverage, while undersmoothing priors produce highly conservative results. Finally, we illustrate our theoretical results by numerical examples.

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。

↑