arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.07532math.PRcs.NAmath.NAmath.STstat.TH
收藏

具有无限可分且厚尾先验测度的良好设定贝叶斯逆问题

Well-posed Bayesian Inverse Problems with Infinitely-Divisible and Heavy-Tailed Prior Measures

Department of mathematics, Simon Fraser University(西蒙菲莎大学数学系)

Bamdad Hosseini

AI总结:

本文提出基于广义伽马分布的新的先验测度,用于p∈(0,1)的ℓp正则化技术,展示其厚尾、非凸和无限可分性质,并探讨无限可分先验测度的尾行为与莱维测度的联系,定义新的函数空间先验测度,解决贝叶斯逆问题的良定性。

摘要:

我们提出了一种新的先验测度,与p∈(0,1)的ℓp正则化技术相关,基于广义伽马分布。我们证明所得到的先验测度是厚尾、非凸和无限可分的。受此启发,我们讨论无限可分先验测度的类别,并建立其尾行为与莱维测度尾行为之间的联系。接着,我们利用纯跳莱维过程的定律,定义新的先验测度,这些测度集中在具有有界变分的函数空间上。这些先验测度作为经典总变分先验的替代品,导致良定义的逆问题。然后,我们在一般设定下研究贝叶斯逆问题的良定性,证明良定性依赖于对数似然函数增长与先验尾行为的平衡,并将结果应用于加性噪声模型和线性问题等特殊情况。最后,我们讨论贝叶斯逆问题的一些实际方面,如其一致近似,并给出三个具体的良定义贝叶斯逆问题实例,这些实例使用厚尾或随机过程先验测度。

英文摘要:

We present a new class of prior measures in connection to $\ell_p$ regularization techniques when $p \in(0,1)$ which is based on the generalized Gamma distribution. We show that the resulting prior measure is heavy-tailed, non-convex and infinitely divisible. Motivated by this observation we discuss the class of infinitely divisible prior measures and draw a connection between their tail behavior and the tail behavior of their L{évy} measures. Next, we use the laws of pure jump L{é}vy processes in order to define new classes of prior measures that are concentrated on the space of functions with bounded variation. These priors serve as an alternative to the classic total variation prior and result in well-defined inverse problems. We then study the well-posedness of Bayesian inverse problems in a general enough setting that encompasses the above mentioned classes of prior measures. We establish that well-posedness relies on a balance between the growth of the log-likelihood function and the tail behavior of the prior and apply our results to special cases such as additive noise models and linear problems. Finally, we discuss some of the practical aspects of Bayesian inverse problems such as their consistent approximation and present three concrete examples of well-posed Bayesian inverse problems with heavy-tailed or stochastic process prior measures.

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。

↑