Machine Learning Trivializing Maps: A First Step Towards Understanding How Flow-Based Samplers Scale Up. (arXiv:2112.15532v1 [hep-lat])

A trivializing map is a field transformation whose Jacobian determinant
exactly cancels the interaction terms in the action, providing a representation
of the theory in terms of a deterministic transformation of a distribution from
which sampling is trivial. Recently, a proof-of-principle study by Albergo,
Kanwar and Shanahan [arXiv:1904.12072] demonstrated that approximations of
trivializing maps can be `machine-learned' by a class of invertible,
differentiable neural models called \textit{normalizing flows}. By ensuring
that the Jacobian determinant can be computed efficiently, …

arxiv learning machine machine learning maps