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 “...
Κύριοι συγγραφείς: | Le, T, Baydin, A, Wood, F |
---|---|
Μορφή: | Conference item |
Έκδοση: |
Journal of Machine Learning Research
2017
|
Παρόμοια τεκμήρια
Παρόμοια τεκμήρια
-
Attention for inference compilation
ανά: Harvey, W, κ.ά.
Έκδοση: (2022) -
Amortized rejection sampling in universal probabilistic programming
ανά: Naderiparizi, S, κ.ά.
Έκδοση: (2022) -
Amortized inference and model learning for probabilistic programming
ανά: Le, TA
Έκδοση: (2019) -
Probabilistic programming with programmable inference
ανά: Mansinghka, Vikash K., κ.ά.
Έκδοση: (2021) -
Efficient probabilistic inference in the quest for physics beyond the standard model
ανά: Baydin, AG, κ.ά.
Έκδοση: (2019)