Continual Repeated Annealed Flow Transport Monte Carlo

Autor:	Matthews, Alexander G. D. G., Arbel, Michael, Rezende, Danilo J., Doucet, Arnaud
Rok vydání:	2022
Předmět:	Statistics - Machine Learning Condensed Matter - Statistical Mechanics Computer Science - Machine Learning High Energy Physics - Lattice
Druh dokumentu:	Working Paper
Popis:	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. Comment: 21 pages, 6 figures Published at International Conference on Machine Learning (ICML) 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2201.13117 Zobrazit plný text záznamu View this record from Arxiv