A Compilation Target for Probabilistic Programming Languages

Brooks Paige, Frank Wood
Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):1935-1943, 2014.

Abstract

Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory. Exploiting this we have defined, developed, and tested a probabilistic programming language intermediate representation language we call probabilistic C, which itself can be compiled to machine code by standard compilers and linked to operating system libraries yielding an efficient, scalable, portable probabilistic programming compilation target. This opens up a new hardware and systems research path for optimizing probabilistic programming systems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v32-paige14, title = {A Compilation Target for Probabilistic Programming Languages}, author = {Paige, Brooks and Wood, Frank}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {1935--1943}, year = {2014}, editor = {Xing, Eric P. and Jebara, Tony}, volume = {32}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/paige14.pdf}, url = {https://proceedings.mlr.press/v32/paige14.html}, abstract = {Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory. Exploiting this we have defined, developed, and tested a probabilistic programming language intermediate representation language we call probabilistic C, which itself can be compiled to machine code by standard compilers and linked to operating system libraries yielding an efficient, scalable, portable probabilistic programming compilation target. This opens up a new hardware and systems research path for optimizing probabilistic programming systems.} }
Endnote
%0 Conference Paper %T A Compilation Target for Probabilistic Programming Languages %A Brooks Paige %A Frank Wood %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-paige14 %I PMLR %P 1935--1943 %U https://proceedings.mlr.press/v32/paige14.html %V 32 %N 2 %X Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory. Exploiting this we have defined, developed, and tested a probabilistic programming language intermediate representation language we call probabilistic C, which itself can be compiled to machine code by standard compilers and linked to operating system libraries yielding an efficient, scalable, portable probabilistic programming compilation target. This opens up a new hardware and systems research path for optimizing probabilistic programming systems.
RIS
TY - CPAPER TI - A Compilation Target for Probabilistic Programming Languages AU - Brooks Paige AU - Frank Wood BT - Proceedings of the 31st International Conference on Machine Learning DA - 2014/06/18 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-paige14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 32 IS - 2 SP - 1935 EP - 1943 L1 - http://proceedings.mlr.press/v32/paige14.pdf UR - https://proceedings.mlr.press/v32/paige14.html AB - Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory. Exploiting this we have defined, developed, and tested a probabilistic programming language intermediate representation language we call probabilistic C, which itself can be compiled to machine code by standard compilers and linked to operating system libraries yielding an efficient, scalable, portable probabilistic programming compilation target. This opens up a new hardware and systems research path for optimizing probabilistic programming systems. ER -
APA
Paige, B. & Wood, F.. (2014). A Compilation Target for Probabilistic Programming Languages. Proceedings of the 31st International Conference on Machine Learning, in Proceedings of Machine Learning Research 32(2):1935-1943 Available from https://proceedings.mlr.press/v32/paige14.html.

Related Material