We propose a novel method for measuring the discrepancy between a set of samples and a desired posterior distribution for Bayesian Inference. Classical methods for assessing sample quality like the effective sample size are not appropriate for scalable Bayesian sampling algorithms, suc
为了提高 Monte Carlo 估计的效率，研究者们正转向有偏的马尔可夫链蒙特卡罗过程，通过权衡渐近精确度和计算速度来实现。本文引入一种基于 Stein's 方法的可计算质量度量来解决这些配合中不精确性带来的新挑战，并将其应用于超参数选择、收敛速率评估和后验推断中，比较精确、有偏和确定性样本序列，并量化样本和目标期望之间的最大偏差。