Continual Repeated Annealed Flow Transport Monte Carlo - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Continual Repeated Annealed Flow Transport Monte Carlo

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.
Fichier principal
Vignette du fichier
matthews22a.pdf (732.39 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03869105 , version 1 (24-11-2022)

Identifiers

  • HAL Id : hal-03869105 , version 1

Cite

Alexander G D G Matthews, Michael Arbel, Danilo J Rezende, Arnaud Doucet. Continual Repeated Annealed Flow Transport Monte Carlo. International Conference on Machine Learning 2022, 2022, Baltimore, United States. ⟨hal-03869105⟩
29 View
11 Download

Share

Gmail Facebook X LinkedIn More