使用混合随机动力学进行采样
Sampling Using Hybrid Stochastic Dynamics
AI总结:
提出一种混合随机动力学框架,通过耦合两种不同区域内的采样动力学,并建立指数收敛速率,改善平均逃逸时间,数值实验验证了其优势。
摘要:
本工作提出一个框架,用于使用混合随机动力学从给定势能的吉布斯分布中采样。在该框架中,两种不同的采样动力学在状态空间的不同区域运行。这两种动力学通过保持目标分布的自然传输条件在界面上耦合。利用一种特殊构造的正则化方案,我们建立了混合动力学到平衡的指数收敛速率。我们还分析了径向对称景观中混合动力学的亚稳态性质,表明混合方案可以改善平均逃逸时间。数值实验进一步证实了这一优势。
英文摘要:
This work proposes a framework for sampling from the Gibbs distribution of a given potential using hybrid stochastic dynamics. In this framework, two distinct sampling dynamics are run in different regions of the state space. The two dynamics are coupled across the interface through natural transmission conditions that preserve the target distribution. Using a specially constructed regularization scheme, we establish an exponential rate of convergence for the hybrid dynamics to equilibrium. We also analyze the metastability properties of the hybrid dynamics in a radially symmetric landscape, showing that the hybrid scheme can improve the mean exit time. This advantage is further confirmed by the numerical experiments.
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。