Flows for Flows: Training Normalizing Flows Between Arbitrary Distributions with Maximum Likelihood Estimation. (arXiv:2211.02487v1 [cs.LG])

Normalizing flows are constructed from a base distribution with a known
density and a diffeomorphism with a tractable Jacobian. The base density of a
normalizing flow can be parameterised by a different normalizing flow, thus
allowing maps to be found between arbitrary distributions. We demonstrate and
explore the utility of this approach and show it is particularly interesting in
the case of conditional normalizing flows and for introducing optimal transport
constraints on maps that are constructed using normalizing flows.

arxiv likelihood maximum likelihood estimation training