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 “...
Үндсэн зохиолчид: | Le, T, Baydin, A, Wood, F |
---|---|
Формат: | Conference item |
Хэвлэсэн: |
Journal of Machine Learning Research
2017
|
Ижил төстэй зүйлс
Ижил төстэй зүйлс
-
Attention for inference compilation
-н: Harvey, W, зэрэг
Хэвлэсэн: (2022) -
Amortized rejection sampling in universal probabilistic programming
-н: Naderiparizi, S, зэрэг
Хэвлэсэн: (2022) -
Amortized inference and model learning for probabilistic programming
-н: Le, TA
Хэвлэсэн: (2019) -
Probabilistic programming with programmable inference
-н: Mansinghka, Vikash K., зэрэг
Хэвлэсэн: (2021) -
Efficient probabilistic inference in the quest for physics beyond the standard model
-н: Baydin, AG, зэрэг
Хэвлэсэн: (2019)