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 2102.04279stat.MLcs.LGcs.NAmath.NA
收藏

约束集成Langevin蒙特卡洛

Constrained Ensemble Langevin Monte Carlo

University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Zhiyan Ding, Qin Li

AI总结:

本文提出Constrained Ensemble Langevin Monte Carlo算法,通过约束方式使用集成近似替代梯度计算,在保持类似经典LMC稳定性的同时大幅降低数值成本。

摘要:

经典的Langevin Monte Carlo(LMC)方法通过沿目标分布的梯度下降样本来寻找目标分布的样本。该方法具有快速收敛率。然而,由于每次迭代都需要计算梯度,其数值成本有时较高。消除梯度计算的一种方法是采用“集成”概念。大量粒子被一起演化,使得相邻粒子能相互提供梯度信息。在本文中,我们讨论了将集成特性集成到LMC中的两种算法及其相关性质。具体而言,我们发现如果直接使用集成近似替代梯度,该算法被称为Ensemble Langevin Monte Carlo,由于存在高方差项而不稳定。如果仅以约束方式用集成近似替换梯度,以防止出现不稳定点,该算法被称为Constrained Ensemble Langevin Monte Carlo,它除了一个集成误差外类似于经典LMC,但去除了大部分梯度计算。

英文摘要:

The classical Langevin Monte Carlo method looks for samples from a target distribution by descending the samples along the gradient of the target distribution. The method enjoys a fast convergence rate. However, the numerical cost is sometimes high because each iteration requires the computation of a gradient. One approach to eliminate the gradient computation is to employ the concept of ``ensemble." A large number of particles are evolved together so the neighboring particles provide gradient information to each other. In this article, we discuss two algorithms that integrate the ensemble feature into LMC and the associated properties. In particular, we find that if one directly surrogates the gradient using the ensemble approximation, the algorithm, termed Ensemble Langevin Monte Carlo, is unstable due to a high variance term. If the gradients are replaced by the ensemble approximations only in a constrained manner, to protect from the unstable points, the algorithm, termed Constrained Ensemble Langevin Monte Carlo, resembles the classical LMC up to an ensemble error but removes most of the gradient computation.

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。

↑