Publications Search
Sam Witty, Alexander Lew, David Jensen, Vikash Mansinghka
Bayesian causal inference via probabilistic program synthesis Miscellaneous
2019.
Abstract | Links | BibTeX | Tags: Probabilistic Programming
@misc{witty2019bayesian,
title = {Bayesian causal inference via probabilistic program synthesis},
author = {Sam Witty and Alexander Lew and David Jensen and Vikash Mansinghka},
url = {https://arxiv.org/pdf/1910.14124.pdf},
year = {2019},
date = {2019-01-01},
journal = {arXiv preprint arXiv:1910.14124},
abstract = {Causal inference can be formalized as Bayesian inference that combines a prior distribution over causal models and likelihoods that account for both observations and interventions. We show that it is possible to implement this approach using a sufficiently expressive probabilistic programming language. Priors are represented using probabilistic programs that generate source code in a domain specific language. Interventions are represented using probabilistic programs that edit this source code to modify the original generative process. This approach makes it straightforward to incorporate data from atomic interventions, as well as shift interventions, variance-scaling interventions, and other interventions that modify causal structure. This approach also enables the use of general-purpose inference machinery for probabilistic programs to infer probable causal structures and parameters from data. This abstract describes a prototype of this approach in the Gen probabilistic programming language.},
keywords = {Probabilistic Programming},
pubstate = {published},
tppubtype = {misc}
}
Causal inference can be formalized as Bayesian inference that combines a prior distribution over causal models and likelihoods that account for both observations and interventions. We show that it is possible to implement this approach using a sufficiently expressive probabilistic programming language. Priors are represented using probabilistic programs that generate source code in a domain specific language. Interventions are represented using probabilistic programs that edit this source code to modify the original generative process. This approach makes it straightforward to incorporate data from atomic interventions, as well as shift interventions, variance-scaling interventions, and other interventions that modify causal structure. This approach also enables the use of general-purpose inference machinery for probabilistic programs to infer probable causal structures and parameters from data. This abstract describes a prototype of this approach in the Gen probabilistic programming language.
Sam Witty, David Jensen
Causal Graphs vs. Causal Programs: The Case of Conditional Branching Proceedings Article
In: First Conference on Probabilistic Programming (ProbProg), 2018.
Abstract | Links | BibTeX | Tags: Probabilistic Programming
@inproceedings{witty2018causal,
title = {Causal Graphs vs. Causal Programs: The Case of Conditional Branching},
author = {Sam Witty and David Jensen},
url = {https://arxiv.org/pdf/2007.07127.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {First Conference on Probabilistic Programming (ProbProg)},
abstract = {We evaluate the performance of graph-based causal discovery algorithms when the generative process is a probabilistic program with conditional branching. Using synthetic experiments, we demonstrate empirically that graph-based causal discovery algorithms are able to learn accurate associational distributions for probabilistic programs with contextsensitive structure, but that those graphs fail to accurately model the effects of interventions on the programs},
keywords = {Probabilistic Programming},
pubstate = {published},
tppubtype = {inproceedings}
}
We evaluate the performance of graph-based causal discovery algorithms when the generative process is a probabilistic program with conditional branching. Using synthetic experiments, we demonstrate empirically that graph-based causal discovery algorithms are able to learn accurate associational distributions for probabilistic programs with contextsensitive structure, but that those graphs fail to accurately model the effects of interventions on the programs
Javier Burroni, Arjun Guha, David Jensen
INTERACTIVE WRITING AND DEBUGGING OF BAYESIAN PROBABILISTIC PROGRAMS Journal Article
In: 2017.
Links | BibTeX | Tags: Probabilistic Programming
@article{burroni2017interactive,
title = {INTERACTIVE WRITING AND DEBUGGING OF BAYESIAN PROBABILISTIC PROGRAMS},
author = {Javier Burroni and Arjun Guha and David Jensen},
url = {https://pps2018.luddy.indiana.edu/files/2017/12/interactive_debugger.pdf},
year = {2017},
date = {2017-01-01},
keywords = {Probabilistic Programming},
pubstate = {published},
tppubtype = {article}
}