Piecewise deterministic Markov processes (PDMPs) are a type of continuous-time Markov process that combine deterministic flows with jumps. Recently, PDMPs have garnered attention within the Monte Carlo community as a potential alternative to traditional Markov chain Monte Carlo (MCMC) methods. The Zig-Zag sampler and the Bouncy particle sampler are commonly used examples of the PDMP methodology which have also yielded impressive theoretical properties, but little is known about their robustness to extreme dependence or isotropy of the target density. It turns out that PDMPs may suffer from poor mixing due to anisotropy and this paper investigates this effect in detail in the stylised but important Gaussian case. To this end, we employ a multi-scale analysis framework in this paper. Our results show that when the Gaussian target distribution has two scales, of order $1$ and $\epsilon$, the computational cost of the Bouncy particle sampler is of order $\epsilon^{-1}$, and the computational cost of the Zig-Zag sampler is either $\epsilon^{-1}$ or $\epsilon^{-2}$, depending on the target distribution. In comparison, the cost of the traditional MCMC methods such as RWM or MALA is of order $\epsilon^{-2}$, at least when the dimensionality of the small component is more than $1$. Therefore, there is a robustness advantage to using PDMPs in this context.
翻译:段分曲马尔可夫过程(PDMPs)是一种将确定流和跳跃结合起来的连续时间马尔可夫过程。最近,PDMPs作为传统马尔可夫链蒙特卡洛(MCMC)方法的替代方法,在蒙特卡洛学界引起了广泛关注。Zig-Zag采样器和Bouncy粒子采样器是PDMP方法的两个常用示例,它们也产生了令人印象深刻的理论性质,但对于目标密度的极端依赖度或各向同性尚知之甚少。事实证明,PDMP可能因各向异性而导致混合不佳,本文将对这一影响进行详细探究,以简明但重要的高斯情况为例。为此,我们在本文中采用了多尺度分析框架。我们的结果表明,当高斯目标分布具有1和ε级量级时,Bouncy粒子采样器的计算成本为ε^{-1},Zig-Zag采样器的计算成本为ε^{-1}或ε^{-2},具体取决于目标分布。相比之下,传统的MCMC方法,如RWM或MALA,其成本至少是ε^{-2},至少当小分量的维数大于1时。因此,在这种情况下使用PDMPs具有鲁棒性优势。