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...
Prif Awduron: | Harvey, W, Munk, A, Baydin, AG, Bergholm, A, Wood, F |
---|---|
Fformat: | Conference item |
Iaith: | English |
Cyhoeddwyd: |
SciTePress
2022
|
Eitemau Tebyg
-
Inference compilation and universal probabilistic programming
gan: Le, T, et al.
Cyhoeddwyd: (2017) -
Efficient probabilistic inference in the quest for physics beyond the standard model
gan: Baydin, AG, et al.
Cyhoeddwyd: (2019) -
ToolPhet: Inference of Compiler Provenance From Stripped Binaries With Emerging Compilation Toolchains
gan: Hohyeon Jang, et al.
Cyhoeddwyd: (2024-01-01) -
Quantitative Inference in a Mechanical Design Compiler
gan: Ward, Allen C., et al.
Cyhoeddwyd: (2004) -
A Theory of Quantitative Inference Applied to a Mechanical Design Compiler
gan: Ward, Allen C.
Cyhoeddwyd: (2004)