Reproduce “Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Sam Staton, Hongseok Yang, Chris Heunen, Ohad Kammar, Frank Wood

The authors develop operational and denotational semantics for a nonrecursive probabilistic language with higher-order functions, continuous distributions, and soft constraints, and prove the accounts agree. They use a functor category to interpret higher-order functions and justify a specified SMC resampling transformation as meaning-preserving. A worked Gaussian example yields posterior probability 0.5 and evidence 0.949; this is not a performance result.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.