The Metropolis-adjusted Langevin (MALA) algorithm is a sampling algorithm that incorporates the gradient of the logarithm of the target density in its proposal distribution. In an earlier joint work \cite{pill:stu:12}, the author had extended the seminal work of \cite{Robe:Rose:98} and showed that in stationarity, MALA applied to an $N$-dimensional approximation of the target will take ${\cal O}(N^{\frac13})$ steps to explore its target measure. It was also shown in \cite{Robe:Rose:98,pill:stu:12} that, as a consequence of the diffusion limit, the MALA algorithm is optimized at an average acceptance probability of $0.574$. In \cite{pere:16}, Pereyra introduced the proximal MALA algorithm where the gradient of the log target density is replaced by the proximal function (mainly aimed at implementing MALA non-differentiable target densities). In this paper, we show that for a wide class of twice differentiable target densities, the proximal MALA enjoys the same optimal scaling as that of MALA in high dimensions and also has an average optimal acceptance probability of $0.574$. The results of this paper thus give the following practically useful guideline: for smooth target densities where it is expensive to compute the gradient while implementing MALA, users may replace the gradient with the corresponding proximal function (that can be often computed relatively cheaply via convex optimization) \emph{without} losing any efficiency. This confirms some of the empirical observations made in \cite{pere:16}.
翻译:大都会调整 Langevin (MALA) 算法是一种取样算法, 它包含其建议分布中目标密度对数的梯度 。 在早期的联合工作\ cite{ pill: stu: 12} 中, 作者扩展了\ cite{ Robe: Rose: 98} 的初始工作, 并显示在固定性中, MALA 应用到目标的一美元- 维近比值将花费$$- cal O} (N ⁇ frac13}) (美元) 来探索其目标度。 它在\ cite{ Robe: Rose: 98, pill: stol: 12} 中也显示, 由于扩散限制的结果, MALA 算法的平均接受概率为0. 574美元。 在\ cite{ peereal: Pereyra 中, 将日志目标密度的梯度的梯度替换为纯度替换为纯度函数( 旨在执行 MALA 不可区别的目标密度 。 在本文中, IMALalalalalalalalalalalal lidealal adal adal erviews erview 。