Inference compilation and universal probabilistic programming
We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that combines the strengths of probabilistic programming and deep learning methods. We call what we do “...
Prif Awduron: | Le, T, Baydin, A, Wood, F |
---|---|
Fformat: | Conference item |
Cyhoeddwyd: |
Journal of Machine Learning Research
2017
|
Eitemau Tebyg
-
Attention for inference compilation
gan: Harvey, W, et al.
Cyhoeddwyd: (2022) -
Amortized rejection sampling in universal probabilistic programming
gan: Naderiparizi, S, et al.
Cyhoeddwyd: (2022) -
Amortized inference and model learning for probabilistic programming
gan: Le, TA
Cyhoeddwyd: (2019) -
Probabilistic programming with programmable inference
gan: Mansinghka, Vikash K., et al.
Cyhoeddwyd: (2021) -
Efficient probabilistic inference in the quest for physics beyond the standard model
gan: Baydin, AG, et al.
Cyhoeddwyd: (2019)