Benutzer: Gast  Login
Titel:

Automatic Posterior Transformation for Likelihood-Free Inference

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Greenberg, David; Nonnenmacher, Marcel; Macke, Jakob
Abstract:
How can one perform Bayesian inference on stochastic simulators with intractable likelihoods? A recent approach is to learn the posterior from adaptively proposed simulations using neural network-based conditional density estimators. However, existing methods are limited to a narrow range of proposal distributions or require importance weighting that can limit performance in practice. Here we present automatic posterior transformation (APT), a new sequential neural posterior estimation method fo...     »
Herausgeber:
Chaudhuri, Kamalika; Salakhutdinov, Ruslan
Kongress- / Buchtitel:
Proceedings of the 36th International Conference on Machine Learning
Band / Teilband / Volume:
97
Verlag / Institution:
PMLR
Verlagsort:
Long Beach, California, USA
Jahr:
2019
Monat:
09--15 Jun
Seiten:
2404--2414
Serientitel:
Proceedings of Machine Learning Research
WWW:
http://proceedings.mlr.press/v97/greenberg19a.html
 BibTeX