流形上的贝叶斯行走
Thomas Bayes' walk on manifolds
摘要：
贝叶斯后验测度的收敛性被认为是在规范的统计设置，其中观察坐在一个几何对象，如一个紧凑的流形，或更一般地在一个紧凑的度量空间验证某些条件。一个自然的几何先验的基础上随机重新标度的热方程的解决方案被认为是。推导了后验收缩率的上界和下界。
英文摘要：
Convergence of the Bayes posterior measure is considered in canonical statistical settings where observations sit on a geometrical object such as a compact manifold, or more generally on a compact metric space verifying some conditions. A natural geometric prior based on randomly rescaled solutions of the heat equation is considered. Upper and lower bound posterior contraction rates are derived.
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。
