Neural Inverse Transform Sampler. (arXiv:2206.11172v1 [cs.LG])

Any explicit functional representation $f$ of a density is hampered by two
main obstacles when we wish to use it as a generative model: designing $f$ so
that sampling is fast, and estimating $Z = \int f$ so that $Z^{-1}f$ integrates
to 1. This becomes increasingly complicated as $f$ itself becomes complicated.
In this paper, we show that when modeling one-dimensional conditional densities
with a neural network, $Z$ can be exactly and efficiently computed by letting
the network represent the …

arxiv lg