Web: http://arxiv.org/abs/2201.13117

June 17, 2022, 1:11 a.m. | Alexander G. D. G. Matthews, Michael Arbel, Danilo J. Rezende, Arnaud Doucet

cs.LG updates on arXiv.org arxiv.org

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 …

arxiv continual flow ml transport

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY