Flow Annealed Importance Sampling Bootstrap. (arXiv:2208.01893v1 [cs.LG])

Normalizing flows are tractable density models that can approximate
complicated target distributions, e.g. Boltzmann distributions of physical
systems. However, current methods for training flows either suffer from
mode-seeking behavior, use samples from the target generated beforehand by
expensive MCMC simulations, or use stochastic losses that have very high
variance. To avoid these problems, we augment flows with annealed importance
sampling (AIS) and minimize the mass covering $\alpha$-divergence with
$\alpha=2$, which minimizes importance weight variance. Our method, Flow AIS
Bootstrap (FAB), …

arxiv bootstrap flow importance lg sampling