2022
Group equivariant neural posterior estimation
Maximilian Dax, Stephen R Green, Jonathan Gair, Michael Deistler, Bernhard Schölkopf, Jakob H. Macke
ICLR 2022poster
Simulation-based inference with conditional neural density estimators is a powerful approach to solving inverse problems in science. However, these methods typically treat the underlying forward model as a black box, with no way to exploit geometric properties such as equivariances. Equivariances ar…