Continual Repeated Annealed Flow Transport Monte Carlo

TL;DR

CRAFT is a novel sampling method that combines sequential Monte Carlo, variational inference, and normalizing flows to improve sampling efficiency and accuracy across annealing temperatures, demonstrated on complex examples.

Contribution

It introduces CRAFT, a new method integrating SMC, variational inference, and normalizing flows for enhanced sampling, outperforming previous methods like ANF and MCMC-based approaches.

Findings

CRAFT outperforms Annealed Flow Transport Monte Carlo in empirical tests.

CRAFT achieves high accuracy in challenging lattice field theory examples.

Incorporating CRAFT into particle MCMC yields highly precise results.

Abstract

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.