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: | , , , , |
|---|---|
| Format: | Conference item |
| Jezik: | English |
| Izdano: |
SciTePress
2022
|