论文标题
持续重复退火流运输蒙特卡洛
Continual Repeated Annealed Flow Transport Monte Carlo
论文作者
论文摘要
我们提出了连续重复的退火流传输蒙特卡洛（CRAFT），该方法结合了连续的蒙特卡洛（SMC）采样器（本身是退火重要性采样的概括）与使用归一化流量的变异推断的方法。直接训练了归一化的流量，可用于使用KL差异进行每个过渡的KL差异在退火温度之间运输。该优化目标本身是使用归一化/SMC近似值估算的。我们从概念上展示并使用多个经验示例，这些实例可以改善退火流运输蒙特卡洛（Arbel等，2021），并在其上建造，也可以在基于马尔可夫链蒙特卡洛（MCMC）基于基于的随机归一化流（Wu等，2020）上。通过将工艺纳入粒子MCMC中，我们表明，这种学识渊博的采样器可以在具有挑战性的晶格场理论示例中获得令人印象深刻的准确结果。
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.
