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...

詳細記述

書誌詳細
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