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 “...
المؤلفون الرئيسيون: | Le, T, Baydin, A, Wood, F |
---|---|
التنسيق: | Conference item |
منشور في: |
Journal of Machine Learning Research
2017
|
مواد مشابهة
-
Attention for inference compilation
حسب: Harvey, W, وآخرون
منشور في: (2022) -
Amortized rejection sampling in universal probabilistic programming
حسب: Naderiparizi, S, وآخرون
منشور في: (2022) -
Amortized inference and model learning for probabilistic programming
حسب: Le, TA
منشور في: (2019) -
Probabilistic programming with programmable inference
حسب: Mansinghka, Vikash K., وآخرون
منشور في: (2021) -
Efficient probabilistic inference in the quest for physics beyond the standard model
حسب: Baydin, AG, وآخرون
منشور في: (2019)