arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1304.6772math.STmath.PRstat.TH
收藏

连续世界中有限信息下贝叶斯推理的脆性

Brittleness of Bayesian Inference Under Finite Information in a Continuous World

Houman Owhadi, Clint Scovel, Tim Sullivan

摘要:

在经典的贝叶斯灵敏度分析框架下,我们推导出了贝叶斯模型后验值的最优上下上界,该贝叶斯模型精确地捕获了数据生成分布的任意大数量的有限维边缘和/或尽可能地接近Prokhorov或全变差度量中的数据生成分布;这些界限表明,在以有限精度测量的任意大数量的样本数据为条件之后,这种模型仍然可能产生最大可能的预测误差。这些结果是通过对测度空间上的测度上的最优化问题发展一种归约演算而得到的。我们使用这种演算来研究产生脆性/鲁棒性的机制,特别是,我们观察到学习和鲁棒性是对立的属性。现在已经很好地理解,偏微分方程的数值分辨率需要满足特定的稳定性条件。在有限信息的连续世界中使用贝叶斯推理是否存在缺失稳定性条件?

英文摘要:

We derive, in the classical framework of Bayesian sensitivity analysis, optimal lower and upper bounds on posterior values obtained from Bayesian models that exactly capture an arbitrarily large number of finite-dimensional marginals of the data-generating distribution and/or that are as close as desired to the data-generating distribution in the Prokhorov or total variation metrics; these bounds show that such models may still make the largest possible prediction error after conditioning on an arbitrarily large number of sample data measured at finite precision. These results are obtained through the development of a reduction calculus for optimization problems over measures on spaces of measures. We use this calculus to investigate the mechanisms that generate brittleness/robustness and, in particular, we observe that learning and robustness are antagonistic properties. It is now well understood that the numerical resolution of PDEs requires the satisfaction of specific stability conditions. Is there a missing stability condition for using Bayesian inference in a continuous world under finite information?

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。

↑