马尔可夫链的Wasserstein去初始化
Wasserstein de-initialization for Markov chains
- University of Passau（帕绍大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文将去初始化框架从全变差距离推广到Wasserstein距离，用于分析吉布斯采样、关键变量采样和切片采样的收敛行为。
AI中文摘要：
本文将由(Roberts和Rosenthal, 2001)针对全变差距离提出的去初始化框架推广到Wasserstein距离。本质上，去初始化捕捉了以下现象：在存在某些结构特征时，马尔可夫链的收敛行为可以归结为某个“更简单”的随机过程的收敛行为。我们的结果允许用一般的Wasserstein距离来衡量这一点。我们应用这些结果来分析吉布斯采样、关键变量采样和切片采样的Wasserstein收敛行为。
英文摘要：
This article generalizes the de-initialization framework, proposed by (Roberts and Rosenthal, 2001) for total variation distance, to Wasserstein distances. In essence, de-initialization captures the phenomenon that in the presence of certain structural features, the convergence behaviour of a Markov chain can be reduced to that of a "simpler" stochastic process. Our results allow to measure this in terms of a general Wasserstein distance. We apply them to analyse the Wasserstein convergence behaviour of Gibbs sampling, linchpin variable sampling and slice sampling.
