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