Attention for inference compilation
We present a neural network architecture for automatic amortized inference in universal probabilistic programs which improves on the performance of current architectures. Our approach extends inference compilation (IC), a technique which uses deep neural networks to approximate a posterior distribut...
主要な著者: | Harvey, W, Munk, A, Baydin, AG, Bergholm, A, Wood, F |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
SciTePress
2022
|
類似資料
-
Inference compilation and universal probabilistic programming
著者:: Le, T, 等
出版事項: (2017) -
Efficient probabilistic inference in the quest for physics beyond the standard model
著者:: Baydin, AG, 等
出版事項: (2019) -
ToolPhet: Inference of Compiler Provenance From Stripped Binaries With Emerging Compilation Toolchains
著者:: Hohyeon Jang, 等
出版事項: (2024-01-01) -
Quantitative Inference in a Mechanical Design Compiler
著者:: Ward, Allen C., 等
出版事項: (2004) -
A Theory of Quantitative Inference Applied to a Mechanical Design Compiler
著者:: Ward, Allen C.
出版事項: (2004)