Scaling exact inference for discrete probabilistic programs
Abstract
Probabilistic programming languages (PPLs) are an expressive means of representing and reasoning about probabilistic models. The computational challenge ofprobabilistic inferenceremains 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 arediscrete. 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.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Nov 13, 2020
- Source ID
- 10.1145/3428208
Entities
People
- Guy Van den Broeck
- Steven Holtzen
- Todd Millstein
Organizations
- Defense Advanced Research Projects Agency
- National Science Foundation
- University of California, Los Angeles