arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.12923math.NAcs.NA
收藏

Ensemble Kalman Sampler:均值场极限与收敛性分析

Ensemble Kalman Sampler: mean-field limit and convergence analysis

Zhiyan Ding, Qin Li

AI总结:

本文研究了 Ensemble Kalman Sampler (EKS) 的理论性质,证明了其连续版本 SDE 系统的适定性及均值场极限为 Fokker-Planck 方程,并得出接近最优的收敛速率,从而为 EKS 作为采样方法的有效性提供了理论依据。

摘要:

Ensemble Kalman Sampler (EKS) 是一种从目标分布中寻找近似 $i.i.d.$ 样本的方法。迄今为止,该算法为何有效及其如何收敛在很大程度上仍属未知。该算法的连续版本是一组耦合的随机微分方程 (SDEs)。在本文中,我们证明了该 SDE 系统的适定性,论证其均值场极限是一个 Fokker-Planck 方程,该方程的长时间平衡态即为目标分布。我们进一步证明其收敛速率接近最优($J^{-1/2}$,其中 $J$ 为粒子数)。这些结果结合 Fokker-Planck 方程向其平衡态的及时收敛性,证明了 EKS 的有效性,并给出了其作为采样方法的收敛速率。

英文摘要:

Ensemble Kalman Sampler (EKS) is a method to find approximately $i.i.d.$ samples from a target distribution. As of today, why the algorithm works and how it converges is mostly unknown. The continuous version of the algorithm is a set of coupled stochastic differential equations (SDEs). In this paper, we prove the wellposedness of the SDE system, justify its mean-field limit is a Fokker-Planck equation, whose long time equilibrium is the target distribution. We further demonstrate that the convergence rate is near-optimal ($J^{-1/2}$, with $J$ being the number of particles). These results, combined with the in-time convergence of the Fokker-Planck equation to its equilibrium, justify the validity of EKS, and provide the convergence rate as a sampling method.

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。

↑