We propose Continual Repeated Annealed Flow Transport Monte Carlo (CRAFT), a method that combines a sequential Monte Carlo (SMC) sampler (itself a generalization of Annealed Importance Sampling) with variational inference using normalizing flows. The normalizing flows are directly trained to transport between annealing temperatures using a KL divergence for each transition. This optimization objective is itself estimated using the normalizing flow/SMC approximation. We show conceptually and using multiple empirical examples that CRAFT improves on Annealed Flow Transport Monte Carlo (Arbel et al., 2021), on which it builds and also on Markov chain Monte Carlo (MCMC) based Stochastic Normalizing Flows (Wu et al., 2020). By incorporating CRAFT within particle MCMC, we show that such learnt samplers can achieve impressively accurate results on a challenging lattice field theory example.

翻译：我们提出了持续重复退火流传输蒙特卡洛方法（CRAFT），该方法将序贯蒙特卡洛采样器（SMC，其本身是退火重要性采样的泛化形式）与基于归一化流的变分推理相结合。归一化流通过针对每个温度过渡的KL散度直接训练以在退火温度间进行传输，该优化目标本身通过归一化流/SMC近似进行估计。我们从概念层面并通过多个实证案例表明，CRAFT在改进其基础方法——退火流传输蒙特卡洛（Arbel等人，2021）——以及基于马尔可夫链蒙特卡洛（MCMC）的随机归一化流（Wu等人，2020）方面表现优异。通过将CRAFT集成到粒子MCMC框架中，我们展示此类学习型采样器能在具有挑战性的晶格场论示例中实现令人瞩目的精确结果。