arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.16634math.PR
收藏

Wasserstein误差界用于连续时间马尔可夫链的聚合

Wasserstein error bounds for aggregations of continuous-time Markov chains

Universität der Bundeswehr München(联邦国防军慕尼黑大学)

Fabian Michel

AI总结:

本文提出了一种基于Wasserstein距离的连续时间马尔可夫链近似误差界,利用粗略里奇曲率控制误差传播,展示了曲率对误差界的影响。

摘要:

我们研究了通过在缩减的状态空间上定义的马尔可夫链对有限的连续时间马尔可夫链进行近似,并为近似瞬态分布提供了在Wasserstein距离下的正式误差界。这些界扩展了之前在总变差距离下的误差界工作,并是向连续时间马尔可夫过程在连续状态空间上的推广的第一步。使用Wasserstein矩阵范数来限制由低维近似引起的动态误差。为了控制累积误差的传播,我们依赖于马尔可夫链的粗略里奇曲率的概念。所提出的界在实际应用中强烈依赖于链的曲率。文献中选取的CTMC示例(我们添加了状态空间上的度量)显示,负曲率导致误差界指数爆炸。另一方面,某些我们称为平移不变的CTMC始终具有非负曲率。当用总变差距离(Wasserstein距离的特例,使用离散度量)测量误差时,曲率也始终非负。如果曲率严格正,则本文提出的界优于之前的工作。

英文摘要:

We study the approximation of a (finite) continuous-time Markov chain by a Markov chain on a reduced state space, and we provide formal error bounds for the approximated transient distributions in the Wasserstein distance. These bounds extend previous work on error bounds in the total variation distance, and are the first step towards a generalization to continuous-time Markov processes with continuous state spaces. A Wasserstein matrix norm is used to bound the error caused by the lower-dimensional approximation of the dynamics. In order to control the propagation of the accumulated error, we rely on the concept of coarse Ricci curvature of a Markov chain. The practical applicability of the presented bounds depends strongly on the curvature of the chain. Examples for CTMCs taken from the literature (where we added a metric on the state space) show that a negative curvature results in exponentially exploding bounds. On the other hand, certain CTMCs which we call translation-invariant always have non-negative curvature. When measuring the error in the total variation distance (a special case of the Wasserstein distance with the discrete metric), the curvature is also always non-negative. If it is strictly positive, the bounds presented in this paper are an improvement over previous work.

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。

↑