software . 2020

Paradoxes of probabilistic programming, and how to condition on events of measure zero with infinitesimal probabilities

Jules Jacobs;
Open Source
  • Published: 09 Oct 2020
  • Publisher: Zenodo
<p>Abstract Probabilistic programming languages allow programmers to write down conditional probability distributions that represent statistical and machine learning models as programs that use observe statements. These programs are run by accumulating likelihood at each observe statement, and using the likelihood to steer random choices and weigh results with inference algorithms such as importance sampling or MCMC. We argue that naive likelihood accumulation does not give desirable semantics and leads to paradoxes when an observe statement is used to condition on a measure-zero event, particularly when the observe statement is executed conditionally on random ...
Persistent Identifiers
arXiv: Computer Science::Programming Languages
Download fromView all 2 versions
Software . 2020
Provider: Datacite
Software . 2020
Provider: Zenodo
Any information missing or wrong?Report an Issue