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 “...
主要な著者: | Le, T, Baydin, A, Wood, F |
---|---|
フォーマット: | Conference item |
出版事項: |
Journal of Machine Learning Research
2017
|
類似資料
-
Attention for inference compilation
著者:: Harvey, W, 等
出版事項: (2022) -
Amortized rejection sampling in universal probabilistic programming
著者:: Naderiparizi, S, 等
出版事項: (2022) -
Amortized inference and model learning for probabilistic programming
著者:: Le, TA
出版事項: (2019) -
Probabilistic programming with programmable inference
著者:: Mansinghka, Vikash K., 等
出版事項: (2021) -
Efficient probabilistic inference in the quest for physics beyond the standard model
著者:: Baydin, AG, 等
出版事項: (2019)