• DOI:10.1109/LICS.2017.8005137
Corpus ID: 215823871

A convenient category for higher-order probability theory

@article{Heunen2017ACC,
  title={A convenient category for higher-order probability theory},
  author={Chris Heunen and Ohad Kammar and S. Staton and Hong-Seok Yang},
  journal={2017 32nd Annual ACM/IEEE Symposium on Logic in Computer Science (LICS)},
  year={2017},
  pages={1-12}
}

• Chris Heunen, Ohad Kammar, +1 author Hong-Seok Yang
• Published 2017
• Computer Science, Mathematics
• 2017 32nd Annual ACM/IEEE Symposium on Logic in Computer Science (LICS)

Higher-order probabilistic programming languages allow programmers to write sophisticated models in machine learning and statistics in a succinct and structured way, but step outside the standard measure-theoretic formalization of probability theory. Programs may use both higher-order functions and continuous distributions, or even define a probability distribution on functions. But standard probability theory does not handle higher-order functions well: the category of measurable spaces is not… Expand

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed