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 1802.08671stat.CO
收藏

Langevin蒙特卡罗和JKO分裂

Langevin Monte Carlo and JKO splitting

Espen Bernton

摘要:

基于离散化朗之万扩散的算法是从高维分布中采样的流行工具。我们开发新的连接等蒙特卡罗算法,Wasserstein梯度流理论,算子分裂方法来解决偏微分方程。特别是,我们表明,近端版本的未调整的Langevin算法对应于一个计划,交替解决两个特定的泛函的梯度流的空间上的概率测度。使用这个角度来看,我们得出一些新的非渐近结果,该算法的收敛性。

英文摘要:

Algorithms based on discretizing Langevin diffusion are popular tools for sampling from high-dimensional distributions. We develop novel connections between such Monte Carlo algorithms, the theory of Wasserstein gradient flow, and the operator splitting approach to solving PDEs. In particular, we show that a proximal version of the Unadjusted Langevin Algorithm corresponds to a scheme that alternates between solving the gradient flows of two specific functionals on the space of probability measures. Using this perspective, we derive some new non-asymptotic results on the convergence properties of this algorithm.

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。

↑