A General-Purpose Probabilistic Programming System with Programmable Inference
Clone or download
Latest commit 9e97710 Dec 11, 2018

README.md

Gen Build Status

Gen: A General-Purpose Probabilistic Programming System with Programmable Inference

Warning: This is unstable and currently unsupported research software. We are currently working on stabilizing the implementation, and developing documentation and tutorials.

(Very fragmentary and out of date) documentation

Tested with Julia 1.0.2

Publications related to Gen

Gen: A General-Purpose Probabilistic Programming System with Programmable Inference. Cusumano-Towner, M. F.; Saad, F. A.; Lew, A.; and Mansinghka, V. K. Technical Report MIT-CSAIL-TR-2018-020, Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts, November 2018. URL.

Incremental inference for probabilistic programs. Cusumano-Towner, M. F.; Bichsel, B.; Gehr, T.; Vechev, M.; and Mansinghka, V. K. In Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), pages 571–585. ACM, 2018. URL.

A design proposal for Gen: Probabilistic programming with fast custom inference via code generation. Cusumano-Towner, M. F.; and Mansinghka, V. K. In Workshop on Machine Learning and Programming Languages (MAPL, co-located with PLDI), pages 52–57. 2018. URL.

Using probabilistic programs as proposals. Cusumano-Towner, M. F.; and Mansinghka, V. K. In Workshop on Probabilistic Programming Languages, Semantics, and Systems (PPS, co-located with POPL). 2018. URL.

Encapsulating models and approximate inference programs in probabilistic modules. Cusumano-Towner, M. F.; and Mansinghka, V. K. In Workshop on Probabilistic Programming Semantics (PPS, co-located with POPL). 2017. URL.

Citing

If you use Gen in your work, please cite using the following:

@techreport{gen2018,
title       = {Gen: A General-Purpose Probabilistic Programming System with Programmable Inference},
author      = {Cusumano-Towner, Marco F. and Saad, Feras A. and Lew, Alexander and Mansinghka, Vikash K.},
year        = {2018},
number      = {MIT-CSAIL-TR-2018-020},
institution = {Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology},
address     = {Cambridge, Massachusetts},
month       = {November},
url_link    = {http://hdl.handle.net/1721.1/119255}
}