arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.02212math.PR
收藏

重尾分布的稳定驱动随机微分方程逼近

Approximation of heavy-tailed distributions via stable-driven SDEs

Lu-Jing Huang, Mateusz B. Majka, Jian Wang

摘要:

许多近似采样算法的构造都是基于这样一个众所周知的事实,即某些Gibbs测度是由布朗运动驱动的遍历随机微分方程(SDEs)的平稳分布。然而,对于一些重尾分布,可以证明相关的随机变量不是指数遍历的,相关的采样算法可能执行得很差。最近在机器学习文献中探索的一个自然的想法是利用具有重尾的随机过程来代替布朗运动。在本文中,我们提供了一个严格的理论框架,研究问题的近似重尾分布通过遍历随机微分方程驱动的对称(旋转不变)$α$稳定的过程。

英文摘要:

Constructions of numerous approximate sampling algorithms are based on the well-known fact that certain Gibbs measures are stationary distributions of ergodic stochastic differential equations (SDEs) driven by the Brownian motion. However, for some heavy-tailed distributions it can be shown that the associated SDE is not exponentially ergodic and that related sampling algorithms may perform poorly. A natural idea that has recently been explored in the machine learning literature in this context is to make use of stochastic processes with heavy tails instead of the Brownian motion. In this paper we provide a rigorous theoretical framework for studying the problem of approximating heavy-tailed distributions via ergodic SDEs driven by symmetric (rotationally invariant) $α$-stable processes.

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。

↑