arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.10731math.OC
收藏

具有小随机扰动的分布系统链扩散过程的稀有事件模拟

On the rare-event simulations of diffusion processes pertaining to a chain of distributed systems with small random perturbations

Getachew K. Befekadu

摘要:

本文考虑一类稀有事件模拟的重要抽样问题,该问题涉及一类分布系统链的扩散过程的行为。我们还假设由$n$ -子系统组成的分布式系统--其中一个小的随机扰动进入第一个子系统,然后随后传递到其他子系统--满足适当的Hörmander条件。在这里,我们提供了一个有效的重要性抽样估计,与指数方差衰减率,涉及这样的扩散过程,也确保了最小的相对估计误差在小噪声限制的罕见事件的概率的渐近。这种分析的框架基本上依赖于大偏差的概率论和与底层分布式系统相关的随机控制问题的值函数之间的连接,其中这样的连接提供了一个计算范例-基于指数倾斜偏置分布-用于构建有效的重要性抽样估计的稀有事件模拟。此外,作为一个副产品,该框架还允许我们导出一个家庭的Hamilton-Jacobi-Bellman,我们也提供了一个可解性条件,相应的最优控制问题。

英文摘要:

In this paper, we consider an importance sampling problem for a certain rare-event simulations involving the behavior of a diffusion process pertaining to a chain of distributed systems with random perturbations. We also assume that the distributed system formed by $n$-subsystems -- in which a small random perturbation enters in the first subsystem and then subsequently transmitted to the other subsystems -- satisfies an appropriate Hörmander condition. Here we provide an efficient importance sampling estimator, with an exponential variance decay rate, for the asymptotics of the probabilities of the rare events involving such a diffusion process that also ensures a minimum relative estimation error in the small noise limit. The framework for such an analysis basically relies on the connection between the probability theory of large deviations and the values functions for a family of stochastic control problems associated with the underlying distributed system, where such a connection provides a computational paradigm -- based on an exponentially-tilted biasing distribution -- for constructing efficient importance sampling estimators for the rare-event simulation. Moreover, as a by-product, the framework also allows us to derive a family of Hamilton-Jacobi-Bellman for which we also provide a solvability condition for the corresponding optimal control problem.

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。

↑