arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.04597cs.LGmath.OC
收藏

一种非光滑电位采样的近似算法

A Proximal Algorithm for Sampling from Non-smooth Potentials

Georgia Institute of Technology(佐治亚理工学院)

Jiaming Liang, Yongxin Chen

摘要:

在这项工作中,我们研究采样问题的非光滑潜力。我们提出了一种新的马尔可夫链蒙特卡罗算法的采样从非光滑的潜力。我们提供了一个非渐近分析我们的算法,并建立了一个多项式时间复杂度$\tilde {\cal O}(d\varepsilon^{-1})$,以获得$\varepsilon$总变异距离的目标密度,优于大多数现有的结果在相同的假设。我们的方法是基于近端束方法和交替采样框架。这个框架需要所谓的限制高斯预言机,它可以被看作是一个采样对应的凸优化中的邻近映射。本文的一个重要贡献是提出了一种快速算法,实现了对具有有界Lipschitz常数的凸非光滑势的约束高斯预言。

英文摘要:

In this work, we examine sampling problems with non-smooth potentials. We propose a novel Markov chain Monte Carlo algorithm for sampling from non-smooth potentials. We provide a non-asymptotical analysis of our algorithm and establish a polynomial-time complexity $\tilde {\cal O}(d\varepsilon^{-1})$ to obtain $\varepsilon$ total variation distance to the target density, better than most existing results under the same assumptions. Our method is based on the proximal bundle method and an alternating sampling framework. This framework requires the so-called restricted Gaussian oracle, which can be viewed as a sampling counterpart of the proximal mapping in convex optimization. One key contribution of this work is a fast algorithm that realizes the restricted Gaussian oracle for any convex non-smooth potential with bounded Lipschitz constant.

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。

↑