标题： 哈密顿蒙特卡罗中余切离散化的次优诊断 显示英文标题

标题： Diagnosing Suboptimal Cotangent Disintegrations in Hamiltonian Monte Carlo

摘要： 当正确调整时，哈密顿蒙特卡罗方法可以解决应用统计学前沿的一些最具挑战性的高维问题，但当调整不当时，性能则令人不满意。 本文中，我展示了如何通过观察一些诊断工具来识别一个关键自由度（余切分解）的次优选择，从而促进该算法的稳健应用。 显示英文摘要

摘要： When properly tuned, Hamiltonian Monte Carlo scales to some of the most challenging high-dimensional problems at the frontiers of applied statistics, but when that tuning is suboptimal the performance leaves much to be desired. In this paper I show how suboptimal choices of one critical degree of freedom, the cotangent disintegration, manifest in readily observed diagnostics that facilitate the robust application of the algorithm.