(OOPSLA 2020) Scaling Exact Inference for Discrete Probabilistic Programs
Probabilistic programming languages (PPLs) are an expressive means of representing and reasoning about probabilistic models. The computational challenge of probabilistic inference remains the primary roadblock for applying PPLs in practice. Inference is fundamentally hard, so there is no one-size-fits all solution. In this work, we target scalable inference for an important class of probabilistic programs: those whose probability distributions are discrete. Discrete distributions are common in many fields, including text analysis, network verification, artificial intelligence, and graph analysis, but they prove to be challenging for existing PPLs.
We develop a domain-specific probabilistic programming language called Dice that features a new approach to exact discrete probabilistic program inference. Dice exploits program structure in order to factorize inference, enabling us to perform exact inference on probabilistic programs with hundreds of thousands of random variables. Our key technical contribution is a new reduction from discrete probabilistic programs to weighted model counting (WMC). This reduction separates the structure of the distribution from its parameters, enabling logical reasoning tools to exploit that structure for probabilistic inference. We (1) show how to compositionally reduce Dice inference to WMC, (2) prove this compilation correct with respect to a denotational semantics, (3) empirically demonstrate the performance benefits over prior approaches, and (4) analyze the types of structure that allow Dice to scale to large probabilistic programs.
Fri 17 JunDisplayed time zone: Pacific Time (US & Canada) change
10:40 - 12:00 | |||
10:40 20mTalk | (OOPSLA 2020) Scaling Exact Inference for Discrete Probabilistic Programs SIGPLAN Track Steven Holtzen Northeastern University, Guy Van den Broeck University of California at Los Angeles, Todd Millstein University of California at Los Angeles | ||
11:00 20mTalk | (POPL 2021) A Pre-Expectation Calculus for Probabilistic Sensitivity SIGPLAN Track Alejandro Aguirre IMDEA Software Institute and T.U. of Madrid (UPM), Gilles Barthe MPI-SP, Germany / IMDEA Software Institute, Spain, Justin Hsu Cornell University, Benjamin Lucien Kaminski Saarland University and University College London, Joost-Pieter Katoen RWTH Aachen University, Christoph Matheja Technical University of Denmark | ||
11:20 20mTalk | (PLDI 2021) On Probabilistic Termination of Functional Programs with Continuous Distributions SIGPLAN Track Raven Beutner CISPA Helmholtz Center for Information Security, Germany, C.-H. Luke Ong University of Oxford | ||
11:40 20mTalk | (POPL 2021) Paradoxes of probabilistic programming SIGPLAN Track Jules Jacobs Radboud University |