Skip to Main content Skip to Navigation
New interface
Conference papers

Annealed Flow Transport Monte Carlo

Michael Arbel 1 Alexander G D G Matthews 2 Arnaud Doucet 2 
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : Annealed Importance Sampling (AIS) and its Sequential Monte Carlo (SMC) extensions are state-of-the-art methods for estimating normalizing constants of probability distributions. We propose here a novel Monte Carlo algorithm, Annealed Flow Transport (AFT), that builds upon AIS and SMC and combines them with normalizing flows (NFs) for improved performance. This method transports a set of particles using not only importance sampling (IS), Markov chain Monte Carlo (MCMC) and resampling steps-as in SMC, but also relies on NFs which are learned sequentially to push particles towards the successive annealed targets. We provide limit theorems for the resulting Monte Carlo estimates of the normalizing constant and expectations with respect to the target distribution. Additionally, we show that a continuous-time scaling limit of the population version of AFT is given by a Feynman-Kac measure which simplifies to the law of a controlled diffusion for expressive NFs. We demonstrate experimentally the benefits and limitations of our methodology on a variety of applications.
Document type :
Conference papers
Complete list of metadata
Contributor : Michael Arbel Connect in order to contact the contributor
Submitted on : Monday, November 29, 2021 - 4:35:46 PM
Last modification on : Wednesday, March 16, 2022 - 3:46:40 AM


2102.07501 (2).pdf
Files produced by the author(s)


  • HAL Id : hal-03455478, version 1



Michael Arbel, Alexander G D G Matthews, Arnaud Doucet. Annealed Flow Transport Monte Carlo. ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Online, France. pp.1-70. ⟨hal-03455478⟩



Record views


Files downloads