论文标题
METFLOW：一种新的有效方法，用于弥合马尔可夫链蒙特卡洛和变异推理之间的差距
MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
论文作者
论文摘要
在此贡献中，我们提出了一种新的计算有效方法，将变异推断（VI）与马尔可夫链蒙特卡洛（MCMC）相结合。这种方法可以与通用的MCMC内核一起使用，但特别适合我们引入的新型MCMC算法系列\ TextIt {MetFlow}，其中使用归一化流量获得了建议。这种MCMC算法产生的边际分布是基于流量的分布的混合物，因此大大提高了变异家族的表达性。与以前的方法遵循此方向不同，我们的方法适合重新培训技巧，并且不依赖于计算昂贵的反向内核。广泛的数值实验显示了对最先进方法的明确计算和性能改进。
In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC). This approach can be used with generic MCMC kernels, but is especially well suited to \textit{MetFlow}, a novel family of MCMC algorithms we introduce, in which proposals are obtained using Normalizing Flows. The marginal distribution produced by such MCMC algorithms is a mixture of flow-based distributions, thus drastically increasing the expressivity of the variational family. Unlike previous methods following this direction, our approach is amenable to the reparametrization trick and does not rely on computationally expensive reverse kernels. Extensive numerical experiments show clear computational and performance improvements over state-of-the-art methods.
