Trace types and denotational semantics for sound programmable inference in probabilistic languages
Name
3371087.pdf
Description
Published version
Size
478.64 KB
Format
Adobe PDF
Checksum (MD5)
3046bf00d0b0584cd7fa4a7a691b9885
Author(s)
Lew, Alexander
Cusumano-Towner, Marco F.
Sherman, Benjamin
Carbin, Michael James
Mansinghka, Vikash K
Date Issued
January 2020
Journal
Proceedings of the ACM on Programming Languages
Publisher
Association for Computing Machinery (ACM)
Citation
Lew, Alexander K. et al. “Trace types and denotational semantics for sound programmable inference in probabilistic languages.” Paper in the Proceedings of the ACM on Programming Languages, 4, POPL, POPL 2020, New Orleans, Louisiana, 19 - 25 January 2020, Association for Computing Machinery (ACM): 19 © 2020 The Author(s)
Version
Final published version
Abstract
Modern probabilistic programming languages aim to formalize and automate key aspects of probabilistic modeling and inference. Many languages provide constructs for programmable inference that enable developers to improve inference speed and accuracy by tailoring an algorithm for use with a particular model or dataset. Unfortunately, it is easy to use these constructs to write unsound programs that appear to run correctly but produce incorrect results. To address this problem, we present a denotational semantics for programmable inference in higher-order probabilistic programming languages, along with a type system that ensures that well-typed inference programs are sound by construction. A central insight is that the type of a probabilistic expression can track the space of its possible execution traces, not just the type of value that it returns, as these traces are often the objects that inference algorithms manipulate. We use our semantics and type system to establish soundness properties of custom inference programs that use constructs for variational, sequential Monte Carlo, importance sampling, and Markov chain Monte Carlo inference.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3371087
