Conference item
Inference compilation and universal probabilistic programming
- Abstract:
-
We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that combines the strengths of probabilistic programming and deep learning methods. We call what we do “compilation of inference” because our method transforms a denotational specification of an inference problem in the form of a probabilistic program written in a universal programming language into ...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Journal of Machine Learning Research Publisher's website
- Host title:
- AI & Statistics - AISTATS 2017
- Journal:
- AI & Statistics 2017 Journal website
- Publication date:
- 2017-04-01
- Acceptance date:
- 2017-01-24
- Event location:
- Lauderdale, Florida, USA
- Event start date:
- 2017-04-20
- Event end date:
- 2047-04-22
Item Description
- Pubs id:
-
pubs:684975
- UUID:
-
uuid:b6f09ebf-9f66-433b-b71b-3980b577047c
- Local pid:
- pubs:684975
- Source identifiers:
-
684975
- Deposit date:
- 2017-03-08
Terms of use
- Copyright holder:
- Wood et al
- Copyright date:
- 2017
- Notes:
- Copyright 2017 by the author(s).
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record