Unifying generative models and exact likelihood-free inference with conditional bijections

Recent work in density estimation uses a bijection $f : X \to Z$ (e.g. an invertible flow or autoregressive model) and a tractable density $p(z)$ (e.g. [[1]](https://arxiv.org/abs/1410.8516) [[2]](http://www.dmi.usherb.ca/~larocheh/projects_nade.html) [[3]](https://arxiv.org/abs/1410.6460) [[4]...

By Kyle Cranmer, Gilles Louppe