arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.00355cs.LGstat.ML
收藏

使用随机插值和前向-后向随机微分方程在高维中进行采样

Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations

École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

Anand Jerry George, Nicolas Macris

AI总结:

提出基于随机插值和前向-后向随机微分方程的扩散算法,在有限时间内将高斯分布样本传输至目标分布,有效解决传统方法难以处理的高维采样问题。

摘要:

我们提出了一类基于扩散的算法,用于在给定非归一化密度的情况下从高维概率分布中抽取样本。理想情况下,我们的方法能在有限时间内将样本从高斯分布传输到指定的目标分布。我们的方法依赖于随机插值框架,定义了一个以时间为索引的概率密度集合,该集合将高斯分布桥接到目标分布。随后,我们推导出一个在每个时刻都遵循上述概率密度的扩散过程。获得这样的扩散过程涉及求解某些 Hamilton-Jacobi-Bellman PDE。我们利用前向-后向随机微分方程(FBSDE)理论结合基于机器学习的方法来求解这些 PDE。通过数值实验,我们证明了我们的算法能够有效地从传统方法难以处理的分布中抽取样本。

英文摘要:

We present a class of diffusion-based algorithms to draw samples from high-dimensional probability distributions given their unnormalized densities. Ideally, our methods can transport samples from a Gaussian distribution to a specified target distribution in finite time. Our approach relies on the stochastic interpolants framework to define a time-indexed collection of probability densities that bridge a Gaussian distribution to the target distribution. Subsequently, we derive a diffusion process that obeys the aforementioned probability density at each time instant. Obtaining such a diffusion process involves solving certain Hamilton-Jacobi-Bellman PDEs. We solve these PDEs using the theory of forward-backward stochastic differential equations (FBSDE) together with machine learning-based methods. Through numerical experiments, we demonstrate that our algorithm can effectively draw samples from distributions that conventional methods struggle to handle.

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。

↑