-
- Description:
Stochaskell is a probabilistic programming language (PPL) designed for portability, allowing models and inference strategies to be written in a single language, but inference to be performed by a variety of PPLs. This is achieved through runtime code generation, whereby code is automatically produced to perform inference via an external PPL on subsets of the model specified by the user. In this way, users can benefit from the diverse probabilistic programming ecosystem without the cost of manually rewriting models in multiple different languages.
Stochaskell also implements a novel method for automatically deriving a Reversible Jump Markov chain Monte Carlo sampler from probabilistic programs that specify the target and proposal distributions. The main challenge in automatically deriving such an inference procedure, in comparison to deriving a generic Metropolis-Hastings sampler, is in calculating the Jacobian adjustment to the proposal acceptance ratio. To achieve this, our approach relies on the interaction of several different components, including automatic differentiation, transformation inversion, and optimised code generation.
- Changes to previous version:
Initial Announcement on mloss.org.
- BibTeX Entry: Download
- Corresponding Paper BibTeX Entry: Download
- Supported Operating Systems: Linux
- Data Formats: Agnostic
- Tags: Probabilistic Programming
- Archive: download here
Comments
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.