arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00682math.PRcs.NAmath.NAstat.COstat.ML
收藏

高维下非精确马尔可夫链蒙特卡罗方法的渐近偏差

Asymptotic bias of inexact Markov Chain Monte Carlo methods in high dimension

Alain Oliviero Durmus, Andreas Eberle

AI总结:

本文为高维非精确MCMC方法(ULA和uHMC)建立了渐近偏差的Wasserstein界,揭示了偏差对维数和步长的依赖关系,并推广到平均场及有限程图模型。

摘要:

非精确马尔可夫链蒙特卡罗方法依赖于不能精确保持目标分布的马尔可夫链。例子包括未调整的朗之万算法(ULA)和未调整的哈密顿蒙特卡罗(uHMC)。本文建立了非精确MCMC方法的不变概率测度与其目标分布之间Wasserstein距离的界,重点在于理解该渐近偏差对维数和离散化步长的精确依赖关系。在假设精确或近似动力学收敛到平衡态的Wasserstein界成立的前提下,我们证明对于ULA和uHMC,渐近偏差依赖于与目标分布或该格式的平稳概率测度相关的关键量。作为一个推论,我们得出结论:对于具有有限相互作用的模型,如平均场模型、有限程图模型及其扰动,渐近偏差对步长和维数的依赖关系与乘积测度的情况相似。

英文摘要:

Inexact Markov Chain Monte Carlo methods rely on Markov chains that do not exactly preserve the target distribution. Examples include the unadjusted Langevin algorithm (ULA) and unadjusted Hamiltonian Monte Carlo (uHMC). This paper establishes bounds on Wasserstein distances between the invariant probability measures of inexact MCMC methods and their target distributions with a focus on understanding the precise dependence of this asymptotic bias on both dimension and discretization step size. Assuming Wasserstein bounds on the convergence to equilibrium of either the exact or the approximate dynamics, we show that for both ULA and uHMC, the asymptotic bias depends on key quantities related to the target distribution or the stationary probability measure of the scheme. As a corollary, we conclude that for models with a limited amount of interactions such as mean-field models, finite range graphical models, and perturbations thereof, the asymptotic bias has a similar dependence on the step size and the dimension as for product measures.

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。

↑